Merge pull request #1714 from slp/install-virglrenderer

container-images: add virglrenderer to vulkan
Merge pull request #1718 from containers/konflux/references/main
2025-07-19 06:35:54 -04:00 · 2025-07-19 06:34:54 -04:00 · 2025-07-19 08:03:10 +00:00 · 2025-07-18 10:54:06 -07:00 · 2025-07-18 09:17:33 -07:00 · 2025-07-18 06:05:26 -04:00
102 changed files with 2078 additions and 270 deletions
--- a/.packit.yaml
+++ b/.packit.yaml
@ -79,7 +79,7 @@ jobs:
    dist_git_branches: &fedora_targets
      - fedora-all
      - epel10
-      - epel9
+      - epel10.0

  - job: koji_build
    trigger: commit
@ -92,4 +92,4 @@ jobs:
    dist_git_branches:
      - fedora-branched # rawhide updates are created automatically
      - epel10
-      - epel9
+      - epel10.0
--- a/.tekton/asahi-llama-server/asahi-llama-server-pull-request.yaml
+++ b/.tekton/asahi-llama-server/asahi-llama-server-pull-request.yaml
@ -0,0 +1,48 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: asahi-llama-server
+    pipelines.appstudio.openshift.io/type: build
+  name: asahi-llama-server-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi-llama-server:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/asahi:on-pr-{{revision}}
+    - ENTRYPOINT=/usr/bin/llama-server.sh
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/asahi-llama-server/asahi-llama-server-push.yaml
+++ b/.tekton/asahi-llama-server/asahi-llama-server-push.yaml
@ -0,0 +1,45 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: asahi-llama-server
+    pipelines.appstudio.openshift.io/type: build
+  name: asahi-llama-server-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi-llama-server:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/asahi:{{revision}}
+    - ENTRYPOINT=/usr/bin/llama-server.sh
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/asahi-rag/asahi-rag-pull-request.yaml
+++ b/.tekton/asahi-rag/asahi-rag-pull-request.yaml
@ -0,0 +1,48 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: asahi-rag
+    pipelines.appstudio.openshift.io/type: build
+  name: asahi-rag-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi-rag:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-d160-m2xlarge/amd64
+    - linux-d160-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.rag
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/asahi:on-pr-{{revision}}
+    - GPU=cpu
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/asahi-rag/asahi-rag-push.yaml
+++ b/.tekton/asahi-rag/asahi-rag-push.yaml
@ -0,0 +1,45 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: asahi-rag
+    pipelines.appstudio.openshift.io/type: build
+  name: asahi-rag-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi-rag:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-d160-m2xlarge/amd64
+    - linux-d160-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.rag
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/asahi:{{revision}}
+    - GPU=cpu
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/asahi-whisper-server/asahi-whisper-server-pull-request.yaml
+++ b/.tekton/asahi-whisper-server/asahi-whisper-server-pull-request.yaml
@ -0,0 +1,48 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: asahi-whisper-server
+    pipelines.appstudio.openshift.io/type: build
+  name: asahi-whisper-server-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi-whisper-server:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/asahi:on-pr-{{revision}}
+    - ENTRYPOINT=/usr/bin/whisper-server.sh
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/asahi-whisper-server/asahi-whisper-server-push.yaml
+++ b/.tekton/asahi-whisper-server/asahi-whisper-server-push.yaml
@ -0,0 +1,45 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: asahi-whisper-server
+    pipelines.appstudio.openshift.io/type: build
+  name: asahi-whisper-server-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi-whisper-server:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/asahi:{{revision}}
+    - ENTRYPOINT=/usr/bin/whisper-server.sh
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/asahi/asahi-pull-request.yaml
+++ b/.tekton/asahi/asahi-pull-request.yaml
@ -0,0 +1,42 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: asahi
+    pipelines.appstudio.openshift.io/type: build
+  name: asahi-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
+  - name: dockerfile
+    value: container-images/asahi/Containerfile
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/asahi/asahi-push.yaml
+++ b/.tekton/asahi/asahi-push.yaml
@ -0,0 +1,39 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: asahi
+    pipelines.appstudio.openshift.io/type: build
+  name: asahi-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/asahi:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
+  - name: dockerfile
+    value: container-images/asahi/Containerfile
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/bats/bats-pull-request.yaml
+++ b/.tekton/bats/bats-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: bats
--- a/.tekton/bats/bats-push.yaml
+++ b/.tekton/bats/bats-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: bats
--- a/.tekton/cann-llama-server/cann-llama-server-pull-request.yaml
+++ b/.tekton/cann-llama-server/cann-llama-server-pull-request.yaml
@ -0,0 +1,48 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: cann-llama-server
+    pipelines.appstudio.openshift.io/type: build
+  name: cann-llama-server-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann-llama-server:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/cann:on-pr-{{revision}}
+    - ENTRYPOINT=/usr/bin/llama-server.sh
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/cann-llama-server/cann-llama-server-push.yaml
+++ b/.tekton/cann-llama-server/cann-llama-server-push.yaml
@ -0,0 +1,45 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: cann-llama-server
+    pipelines.appstudio.openshift.io/type: build
+  name: cann-llama-server-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann-llama-server:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/cann:{{revision}}
+    - ENTRYPOINT=/usr/bin/llama-server.sh
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/cann-rag/cann-rag-pull-request.yaml
+++ b/.tekton/cann-rag/cann-rag-pull-request.yaml
@ -0,0 +1,48 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: cann-rag
+    pipelines.appstudio.openshift.io/type: build
+  name: cann-rag-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann-rag:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-d160-m2xlarge/amd64
+    - linux-d160-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.rag
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/cann:on-pr-{{revision}}
+    - GPU=cpu
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/cann-rag/cann-rag-push.yaml
+++ b/.tekton/cann-rag/cann-rag-push.yaml
@ -0,0 +1,45 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: cann-rag
+    pipelines.appstudio.openshift.io/type: build
+  name: cann-rag-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann-rag:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-d160-m2xlarge/amd64
+    - linux-d160-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.rag
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/cann:{{revision}}
+    - GPU=cpu
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/cann-whisper-server/cann-whisper-server-pull-request.yaml
+++ b/.tekton/cann-whisper-server/cann-whisper-server-pull-request.yaml
@ -0,0 +1,48 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: cann-whisper-server
+    pipelines.appstudio.openshift.io/type: build
+  name: cann-whisper-server-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann-whisper-server:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/cann:on-pr-{{revision}}
+    - ENTRYPOINT=/usr/bin/whisper-server.sh
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/cann-whisper-server/cann-whisper-server-push.yaml
+++ b/.tekton/cann-whisper-server/cann-whisper-server-push.yaml
@ -0,0 +1,45 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: cann-whisper-server
+    pipelines.appstudio.openshift.io/type: build
+  name: cann-whisper-server-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann-whisper-server:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/cann:{{revision}}
+    - ENTRYPOINT=/usr/bin/whisper-server.sh
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/cann/cann-pull-request.yaml
+++ b/.tekton/cann/cann-pull-request.yaml
@ -0,0 +1,42 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: cann
+    pipelines.appstudio.openshift.io/type: build
+  name: cann-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
+  - name: dockerfile
+    value: container-images/cann/Containerfile
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/cann/cann-push.yaml
+++ b/.tekton/cann/cann-push.yaml
@ -0,0 +1,39 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: cann
+    pipelines.appstudio.openshift.io/type: build
+  name: cann-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/cann:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
+  - name: dockerfile
+    value: container-images/cann/Containerfile
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/cuda-llama-server/cuda-llama-server-pull-request.yaml
+++ b/.tekton/cuda-llama-server/cuda-llama-server-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: cuda-llama-server
@ -29,6 +29,7 @@ spec:
  - name: build-platforms
    value:
    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
  - name: dockerfile
    value: container-images/common/Containerfile.entrypoint
  - name: parent-image
--- a/.tekton/cuda-llama-server/cuda-llama-server-push.yaml
+++ b/.tekton/cuda-llama-server/cuda-llama-server-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: cuda-llama-server
@ -26,6 +26,7 @@ spec:
  - name: build-platforms
    value:
    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
  - name: dockerfile
    value: container-images/common/Containerfile.entrypoint
  - name: parent-image
--- a/.tekton/cuda-rag/cuda-rag-pull-request.yaml
+++ b/.tekton/cuda-rag/cuda-rag-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: cuda-rag
@ -29,6 +29,7 @@ spec:
  - name: build-platforms
    value:
    - linux-d160-m2xlarge/amd64
+    - linux-d160-m2xlarge/arm64
  - name: dockerfile
    value: container-images/common/Containerfile.rag
  - name: parent-image
--- a/.tekton/cuda-rag/cuda-rag-push.yaml
+++ b/.tekton/cuda-rag/cuda-rag-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: cuda-rag
@ -26,6 +26,7 @@ spec:
  - name: build-platforms
    value:
    - linux-d160-m2xlarge/amd64
+    - linux-d160-m2xlarge/arm64
  - name: dockerfile
    value: container-images/common/Containerfile.rag
  - name: parent-image
--- a/.tekton/cuda-whisper-server/cuda-whisper-server-pull-request.yaml
+++ b/.tekton/cuda-whisper-server/cuda-whisper-server-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: cuda-whisper-server
@ -29,6 +29,7 @@ spec:
  - name: build-platforms
    value:
    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
  - name: dockerfile
    value: container-images/common/Containerfile.entrypoint
  - name: parent-image
--- a/.tekton/cuda-whisper-server/cuda-whisper-server-push.yaml
+++ b/.tekton/cuda-whisper-server/cuda-whisper-server-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: cuda-whisper-server
@ -26,6 +26,7 @@ spec:
  - name: build-platforms
    value:
    - linux-m2xlarge/amd64
+    - linux-m2xlarge/arm64
  - name: dockerfile
    value: container-images/common/Containerfile.entrypoint
  - name: parent-image
--- a/.tekton/cuda/cuda-pull-request.yaml
+++ b/.tekton/cuda/cuda-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: cuda
@ -29,6 +29,7 @@ spec:
  - name: build-platforms
    value:
    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
  - name: dockerfile
    value: container-images/cuda/Containerfile
  pipelineRef:
--- a/.tekton/cuda/cuda-push.yaml
+++ b/.tekton/cuda/cuda-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: cuda
@ -26,6 +26,7 @@ spec:
  - name: build-platforms
    value:
    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
  - name: dockerfile
    value: container-images/cuda/Containerfile
  pipelineRef:
--- a/.tekton/integration/pipelines/bats-integration.yaml
+++ b/.tekton/integration/pipelines/bats-integration.yaml
@ -52,10 +52,6 @@ spec:
    params:
    - name: image
      value: $(tasks.init.results.bats-image)
-    - name: git-url
-      value: $(params.git-url)
-    - name: git-revision
-      value: $(params.git-revision)
    - name: envs
      value:
      - RAMALAMA_IMAGE=$(tasks.init.results.ramalama-image)
--- a/.tekton/integration/tasks/test-vm-cmd.yaml
+++ b/.tekton/integration/tasks/test-vm-cmd.yaml
@ -9,10 +9,6 @@ spec:
    description: The platform of the VM to provision
  - name: image
    description: The image to use when setting up the test environment
-  - name: git-url
-    description: The URL of the source code repository
-  - name: git-revision
-    description: The revision of the source code to test
  - name: cmd
    description: The command to run
  - name: envs
@ -38,10 +34,6 @@ spec:
      name: ssh
    workingDir: /var/workdir
    env:
-    - name: GIT_URL
-      value: $(params.git-url)
-    - name: GIT_REVISION
-      value: $(params.git-revision)
    - name: TEST_IMAGE
      value: $(params.image)
    - name: TEST_CMD
@ -57,13 +49,7 @@ spec:
      }

      log Install packages
-      dnf -y install openssh-clients rsync git-core jq
-
-      log Clone source
-      git clone -n "$GIT_URL" source
-      pushd source
-      git checkout "$GIT_REVISION"
-      popd
+      dnf -y install openssh-clients rsync jq

      log Prepare connection

@ -107,7 +93,7 @@ spec:
      --security-opt label=disable \
      --security-opt unmask=/proc/* \
      --device /dev/net/tun \
-      -v \$PWD/source:/src \
+      --device /dev/fuse \
      ${PODMAN_ENV[*]} \
      $TEST_IMAGE $TEST_CMD
      SCRIPTEOF
@ -119,7 +105,7 @@ spec:
        export SSH_ARGS="-o StrictHostKeyChecking=no -o ServerAliveInterval=60 -o ServerAliveCountMax=10"
        # ssh once before rsync to retrieve the host key
        ssh $SSH_ARGS "$SSH_HOST" "uname -a"
-        rsync -ra scripts source "$SSH_HOST:$BUILD_DIR"
+        rsync -ra scripts "$SSH_HOST:$BUILD_DIR"
        ssh $SSH_ARGS "$SSH_HOST" "$BUILD_DIR/scripts/test.sh"
        log End VM exec
      else
--- a/.tekton/intel-gpu-llama-server/intel-gpu-llama-server-pull-request.yaml
+++ b/.tekton/intel-gpu-llama-server/intel-gpu-llama-server-pull-request.yaml
@ -0,0 +1,47 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: intel-gpu-llama-server
+    pipelines.appstudio.openshift.io/type: build
+  name: intel-gpu-llama-server-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu-llama-server:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:on-pr-{{revision}}
+    - ENTRYPOINT=/usr/bin/llama-server.sh
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/intel-gpu-llama-server/intel-gpu-llama-server-push.yaml
+++ b/.tekton/intel-gpu-llama-server/intel-gpu-llama-server-push.yaml
@ -0,0 +1,44 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: intel-gpu-llama-server
+    pipelines.appstudio.openshift.io/type: build
+  name: intel-gpu-llama-server-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu-llama-server:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:{{revision}}
+    - ENTRYPOINT=/usr/bin/llama-server.sh
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/intel-gpu-rag/intel-gpu-rag-pull-request.yaml
+++ b/.tekton/intel-gpu-rag/intel-gpu-rag-pull-request.yaml
@ -0,0 +1,47 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: intel-gpu-rag
+    pipelines.appstudio.openshift.io/type: build
+  name: intel-gpu-rag-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu-rag:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-d160-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.rag
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:on-pr-{{revision}}
+    - GPU=cpu
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/intel-gpu-rag/intel-gpu-rag-push.yaml
+++ b/.tekton/intel-gpu-rag/intel-gpu-rag-push.yaml
@ -0,0 +1,44 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: intel-gpu-rag
+    pipelines.appstudio.openshift.io/type: build
+  name: intel-gpu-rag-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu-rag:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-d160-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.rag
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:{{revision}}
+    - GPU=cpu
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/intel-gpu-whisper-server/intel-gpu-whisper-server-pull-request.yaml
+++ b/.tekton/intel-gpu-whisper-server/intel-gpu-whisper-server-pull-request.yaml
@ -0,0 +1,47 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: intel-gpu-whisper-server
+    pipelines.appstudio.openshift.io/type: build
+  name: intel-gpu-whisper-server-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu-whisper-server:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:on-pr-{{revision}}
+    - ENTRYPOINT=/usr/bin/whisper-server.sh
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/intel-gpu-whisper-server/intel-gpu-whisper-server-push.yaml
+++ b/.tekton/intel-gpu-whisper-server/intel-gpu-whisper-server-push.yaml
@ -0,0 +1,44 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: intel-gpu-whisper-server
+    pipelines.appstudio.openshift.io/type: build
+  name: intel-gpu-whisper-server-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu-whisper-server:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:{{revision}}
+    - ENTRYPOINT=/usr/bin/whisper-server.sh
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/intel-gpu/intel-gpu-pull-request.yaml
+++ b/.tekton/intel-gpu/intel-gpu-pull-request.yaml
@ -0,0 +1,41 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: intel-gpu
+    pipelines.appstudio.openshift.io/type: build
+  name: intel-gpu-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+  - name: dockerfile
+    value: container-images/intel-gpu/Containerfile
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/intel-gpu/intel-gpu-push.yaml
+++ b/.tekton/intel-gpu/intel-gpu-push.yaml
@ -0,0 +1,38 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: intel-gpu
+    pipelines.appstudio.openshift.io/type: build
+  name: intel-gpu-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/intel-gpu:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+  - name: dockerfile
+    value: container-images/intel-gpu/Containerfile
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/llama-stack/llama-stack-pull-request.yaml
+++ b/.tekton/llama-stack/llama-stack-pull-request.yaml
@ -0,0 +1,42 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: llama-stack
+    pipelines.appstudio.openshift.io/type: build
+  name: llama-stack-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/llama-stack:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
+  - name: dockerfile
+    value: container-images/llama-stack/Containerfile
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/llama-stack/llama-stack-push.yaml
+++ b/.tekton/llama-stack/llama-stack-push.yaml
@ -0,0 +1,39 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: llama-stack
+    pipelines.appstudio.openshift.io/type: build
+  name: llama-stack-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/llama-stack:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
+  - name: dockerfile
+    value: container-images/llama-stack/Containerfile
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/musa-llama-server/musa-llama-server-pull-request.yaml
+++ b/.tekton/musa-llama-server/musa-llama-server-pull-request.yaml
@ -0,0 +1,47 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: musa-llama-server
+    pipelines.appstudio.openshift.io/type: build
+  name: musa-llama-server-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa-llama-server:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/musa:on-pr-{{revision}}
+    - ENTRYPOINT=/usr/bin/llama-server.sh
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/musa-llama-server/musa-llama-server-push.yaml
+++ b/.tekton/musa-llama-server/musa-llama-server-push.yaml
@ -0,0 +1,44 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: musa-llama-server
+    pipelines.appstudio.openshift.io/type: build
+  name: musa-llama-server-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa-llama-server:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/musa:{{revision}}
+    - ENTRYPOINT=/usr/bin/llama-server.sh
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/musa-rag/musa-rag-pull-request.yaml
+++ b/.tekton/musa-rag/musa-rag-pull-request.yaml
@ -0,0 +1,47 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: musa-rag
+    pipelines.appstudio.openshift.io/type: build
+  name: musa-rag-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa-rag:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-d160-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.rag
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/musa:on-pr-{{revision}}
+    - GPU=musa
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/musa-rag/musa-rag-push.yaml
+++ b/.tekton/musa-rag/musa-rag-push.yaml
@ -0,0 +1,44 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: musa-rag
+    pipelines.appstudio.openshift.io/type: build
+  name: musa-rag-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa-rag:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-d160-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.rag
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/musa:{{revision}}
+    - GPU=musa
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/musa-whisper-server/musa-whisper-server-pull-request.yaml
+++ b/.tekton/musa-whisper-server/musa-whisper-server-pull-request.yaml
@ -0,0 +1,47 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: musa-whisper-server
+    pipelines.appstudio.openshift.io/type: build
+  name: musa-whisper-server-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa-whisper-server:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa:on-pr-{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/musa:on-pr-{{revision}}
+    - ENTRYPOINT=/usr/bin/whisper-server.sh
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/musa-whisper-server/musa-whisper-server-push.yaml
+++ b/.tekton/musa-whisper-server/musa-whisper-server-push.yaml
@ -0,0 +1,44 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: musa-whisper-server
+    pipelines.appstudio.openshift.io/type: build
+  name: musa-whisper-server-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa-whisper-server:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-m2xlarge/amd64
+  - name: dockerfile
+    value: container-images/common/Containerfile.entrypoint
+  - name: parent-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa:{{revision}}
+  - name: build-args
+    value:
+    - PARENT=quay.io/redhat-user-workloads/ramalama-tenant/musa:{{revision}}
+    - ENTRYPOINT=/usr/bin/whisper-server.sh
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/musa/musa-pull-request.yaml
+++ b/.tekton/musa/musa-pull-request.yaml
@ -0,0 +1,41 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: musa
+    pipelines.appstudio.openshift.io/type: build
+  name: musa-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+  - name: dockerfile
+    value: container-images/musa/Containerfile
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/musa/musa-push.yaml
+++ b/.tekton/musa/musa-push.yaml
@ -0,0 +1,38 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: musa
+    pipelines.appstudio.openshift.io/type: build
+  name: musa-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/musa:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+  - name: dockerfile
+    value: container-images/musa/Containerfile
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/openvino/openvino-pull-request.yaml
+++ b/.tekton/openvino/openvino-pull-request.yaml
@ -0,0 +1,41 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: openvino
+    pipelines.appstudio.openshift.io/type: build
+  name: openvino-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/openvino:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+  - name: dockerfile
+    value: container-images/openvino/Containerfile
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/openvino/openvino-push.yaml
+++ b/.tekton/openvino/openvino-push.yaml
@ -0,0 +1,38 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: openvino
+    pipelines.appstudio.openshift.io/type: build
+  name: openvino-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/openvino:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+  - name: dockerfile
+    value: container-images/openvino/Containerfile
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/pipelines/pull-request-pipeline.yaml
+++ b/.tekton/pipelines/pull-request-pipeline.yaml
@ -113,7 +113,7 @@ spec:
      - name: name
        value: init
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-init:0.2@sha256:66e90d31e1386bf516fb548cd3e3f0082b5d0234b8b90dbf9e0d4684b70dbe1a
+        value: quay.io/konflux-ci/tekton-catalog/task-init:0.2@sha256:1d8221c84f91b923d89de50bf16481ea729e3b68ea04a9a7cbe8485ddbb27ee6
      - name: kind
        value: task
      resolver: bundles
@ -163,7 +163,7 @@ spec:
      - name: name
        value: prefetch-dependencies-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-prefetch-dependencies-oci-ta:0.2@sha256:f10a4841e6f75fbb314b1d8cbf14f652499c1fe7f59e59aed59f7431c680aa17
+        value: quay.io/konflux-ci/tekton-catalog/task-prefetch-dependencies-oci-ta:0.2@sha256:092491ac0f6e1009d10c58a1319d1029371bf637cc1293cceba53c6da5314ed1
      - name: kind
        value: task
      resolver: bundles
@ -225,7 +225,7 @@ spec:
      - name: name
        value: buildah-remote-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-buildah-remote-oci-ta:0.4@sha256:5b8d51fa889cdac873750904c3fccc0cca1c4f65af16902ebb2b573151f80657
+        value: quay.io/konflux-ci/tekton-catalog/task-buildah-remote-oci-ta:0.4@sha256:9e866d4d0489a6ab84ae263db416c9f86d2d6117ef4444f495a0e97388ae3ac0
      - name: kind
        value: task
      resolver: bundles
@ -254,7 +254,7 @@ spec:
      - name: name
        value: build-image-index
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-build-image-index:0.1@sha256:846dc9975914f31380ec2712fdbac9df3b06c00a9cc7df678315a7f97145efc2
+        value: quay.io/konflux-ci/tekton-catalog/task-build-image-index:0.1@sha256:3499772af90aad0d3935629be6d37dd9292195fb629e6f43ec839c7f545a0faa
      - name: kind
        value: task
      resolver: bundles
@ -285,8 +285,6 @@ spec:
    params:
    - name: image
      value: $(params.test-image)@$(tasks.wait-for-test-image.results.digest)
-    - name: source-artifact
-      value: $(tasks.prefetch-dependencies.results.SOURCE_ARTIFACT)
    - name: envs
      value:
      - $(params.test-envs[*])
@ -364,7 +362,7 @@ spec:
      - name: name
        value: clair-scan
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-clair-scan:0.2@sha256:d354939892f3a904223ec080cc3771bd11931085a5d202323ea491ee8e8c5e43
+        value: quay.io/konflux-ci/tekton-catalog/task-clair-scan:0.2@sha256:417f44117f8d87a4a62fea6589b5746612ac61640b454dbd88f74892380411f2
      - name: kind
        value: task
      resolver: bundles
@ -384,7 +382,7 @@ spec:
      - name: name
        value: ecosystem-cert-preflight-checks
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-ecosystem-cert-preflight-checks:0.2@sha256:abbe195626eec925288df6425679559025d1be4af5ae70ca6dbbcb49ad3bf08b
+        value: quay.io/konflux-ci/tekton-catalog/task-ecosystem-cert-preflight-checks:0.2@sha256:f99d2bdb02f13223d494077a2cde31418d09369f33c02134a8e7e5fad2f61eda
      - name: kind
        value: task
      resolver: bundles
@ -410,7 +408,7 @@ spec:
      - name: name
        value: sast-snyk-check-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-sast-snyk-check-oci-ta:0.4@sha256:e61f541189b30d14292ef8df36ccaf13f7feb2378fed5f74cb6293b3e79eb687
+        value: quay.io/konflux-ci/tekton-catalog/task-sast-snyk-check-oci-ta:0.4@sha256:fe5e5ba3a72632cd505910de2eacd62c9d11ed570c325173188f8d568ac60771
      - name: kind
        value: task
      resolver: bundles
@ -432,7 +430,7 @@ spec:
      - name: name
        value: clamav-scan
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-clamav-scan:0.2@sha256:9cab95ac9e833d77a63c079893258b73b8d5a298d93aaf9bdd6722471bc2f338
+        value: quay.io/konflux-ci/tekton-catalog/task-clamav-scan:0.2@sha256:7749146f7e4fe530846f1b15c9366178ec9f44776ef1922a60d3e7e2b8c6426b
      - name: kind
        value: task
      resolver: bundles
@ -477,7 +475,7 @@ spec:
      - name: name
        value: sast-coverity-check-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-sast-coverity-check-oci-ta:0.3@sha256:c926568ce63e4f63e18bb6a4178caca2e8192f6e3b830bbcd354e6485d29458c
+        value: quay.io/konflux-ci/tekton-catalog/task-sast-coverity-check-oci-ta:0.3@sha256:f9ca942208dc2e63b479384ccc56a611cc793397ecc837637b5b9f89c2ecbefe
      - name: kind
        value: task
      resolver: bundles
@ -524,7 +522,7 @@ spec:
      - name: name
        value: sast-shell-check-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-sast-shell-check-oci-ta:0.1@sha256:808bcaf75271db6a999f53fdefb973a385add94a277d37fbd3df68f8ac7dfaa3
+        value: quay.io/konflux-ci/tekton-catalog/task-sast-shell-check-oci-ta:0.1@sha256:bf7bdde00b7212f730c1356672290af6f38d070da2c8a316987b5c32fd49e0b9
      - name: kind
        value: task
      resolver: bundles
@ -595,7 +593,7 @@ spec:
      - name: name
        value: push-dockerfile-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-push-dockerfile-oci-ta:0.1@sha256:5d8013b6a27bbc5e4ff261144616268f28417ed0950d583ef36349fcd59d3d3d
+        value: quay.io/konflux-ci/tekton-catalog/task-push-dockerfile-oci-ta:0.1@sha256:8c75c4a747e635e5f3e12266a3bb6e5d3132bf54e37eaa53d505f89897dd8eca
      - name: kind
        value: task
      resolver: bundles
@ -631,7 +629,7 @@ spec:
      - name: name
        value: show-sbom
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-show-sbom:0.1@sha256:1b1df4da95966d08ac6a5b8198710e09e68b5c2cdc707c37d9d19769e65884b2
+        value: quay.io/konflux-ci/tekton-catalog/task-show-sbom:0.1@sha256:86c069cac0a669797e8049faa8aa4088e70ff7fcd579d5bdc37626a9e0488a05
      - name: kind
        value: task
      resolver: bundles
--- a/.tekton/pipelines/push-pipeline.yaml
+++ b/.tekton/pipelines/push-pipeline.yaml
@ -113,7 +113,7 @@ spec:
      - name: name
        value: init
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-init:0.2@sha256:66e90d31e1386bf516fb548cd3e3f0082b5d0234b8b90dbf9e0d4684b70dbe1a
+        value: quay.io/konflux-ci/tekton-catalog/task-init:0.2@sha256:1d8221c84f91b923d89de50bf16481ea729e3b68ea04a9a7cbe8485ddbb27ee6
      - name: kind
        value: task
      resolver: bundles
@ -163,7 +163,7 @@ spec:
      - name: name
        value: prefetch-dependencies-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-prefetch-dependencies-oci-ta:0.2@sha256:f10a4841e6f75fbb314b1d8cbf14f652499c1fe7f59e59aed59f7431c680aa17
+        value: quay.io/konflux-ci/tekton-catalog/task-prefetch-dependencies-oci-ta:0.2@sha256:092491ac0f6e1009d10c58a1319d1029371bf637cc1293cceba53c6da5314ed1
      - name: kind
        value: task
      resolver: bundles
@ -225,7 +225,7 @@ spec:
      - name: name
        value: buildah-remote-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-buildah-remote-oci-ta:0.4@sha256:5b8d51fa889cdac873750904c3fccc0cca1c4f65af16902ebb2b573151f80657
+        value: quay.io/konflux-ci/tekton-catalog/task-buildah-remote-oci-ta:0.4@sha256:9e866d4d0489a6ab84ae263db416c9f86d2d6117ef4444f495a0e97388ae3ac0
      - name: kind
        value: task
      resolver: bundles
@ -254,7 +254,7 @@ spec:
      - name: name
        value: build-image-index
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-build-image-index:0.1@sha256:846dc9975914f31380ec2712fdbac9df3b06c00a9cc7df678315a7f97145efc2
+        value: quay.io/konflux-ci/tekton-catalog/task-build-image-index:0.1@sha256:3499772af90aad0d3935629be6d37dd9292195fb629e6f43ec839c7f545a0faa
      - name: kind
        value: task
      resolver: bundles
@ -285,8 +285,6 @@ spec:
    params:
    - name: image
      value: $(params.test-image)@$(tasks.wait-for-test-image.results.digest)
-    - name: source-artifact
-      value: $(tasks.prefetch-dependencies.results.SOURCE_ARTIFACT)
    - name: envs
      value:
      - $(params.test-envs[*])
@ -364,7 +362,7 @@ spec:
      - name: name
        value: clair-scan
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-clair-scan:0.2@sha256:d354939892f3a904223ec080cc3771bd11931085a5d202323ea491ee8e8c5e43
+        value: quay.io/konflux-ci/tekton-catalog/task-clair-scan:0.2@sha256:417f44117f8d87a4a62fea6589b5746612ac61640b454dbd88f74892380411f2
      - name: kind
        value: task
      resolver: bundles
@ -384,7 +382,7 @@ spec:
      - name: name
        value: ecosystem-cert-preflight-checks
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-ecosystem-cert-preflight-checks:0.2@sha256:abbe195626eec925288df6425679559025d1be4af5ae70ca6dbbcb49ad3bf08b
+        value: quay.io/konflux-ci/tekton-catalog/task-ecosystem-cert-preflight-checks:0.2@sha256:f99d2bdb02f13223d494077a2cde31418d09369f33c02134a8e7e5fad2f61eda
      - name: kind
        value: task
      resolver: bundles
@ -410,7 +408,7 @@ spec:
      - name: name
        value: sast-snyk-check-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-sast-snyk-check-oci-ta:0.4@sha256:e61f541189b30d14292ef8df36ccaf13f7feb2378fed5f74cb6293b3e79eb687
+        value: quay.io/konflux-ci/tekton-catalog/task-sast-snyk-check-oci-ta:0.4@sha256:fe5e5ba3a72632cd505910de2eacd62c9d11ed570c325173188f8d568ac60771
      - name: kind
        value: task
      resolver: bundles
@ -432,7 +430,7 @@ spec:
      - name: name
        value: clamav-scan
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-clamav-scan:0.2@sha256:9cab95ac9e833d77a63c079893258b73b8d5a298d93aaf9bdd6722471bc2f338
+        value: quay.io/konflux-ci/tekton-catalog/task-clamav-scan:0.2@sha256:7749146f7e4fe530846f1b15c9366178ec9f44776ef1922a60d3e7e2b8c6426b
      - name: kind
        value: task
      resolver: bundles
@ -477,7 +475,7 @@ spec:
      - name: name
        value: sast-coverity-check-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-sast-coverity-check-oci-ta:0.3@sha256:c926568ce63e4f63e18bb6a4178caca2e8192f6e3b830bbcd354e6485d29458c
+        value: quay.io/konflux-ci/tekton-catalog/task-sast-coverity-check-oci-ta:0.3@sha256:f9ca942208dc2e63b479384ccc56a611cc793397ecc837637b5b9f89c2ecbefe
      - name: kind
        value: task
      resolver: bundles
@ -524,7 +522,7 @@ spec:
      - name: name
        value: sast-shell-check-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-sast-shell-check-oci-ta:0.1@sha256:808bcaf75271db6a999f53fdefb973a385add94a277d37fbd3df68f8ac7dfaa3
+        value: quay.io/konflux-ci/tekton-catalog/task-sast-shell-check-oci-ta:0.1@sha256:bf7bdde00b7212f730c1356672290af6f38d070da2c8a316987b5c32fd49e0b9
      - name: kind
        value: task
      resolver: bundles
@ -595,7 +593,7 @@ spec:
      - name: name
        value: push-dockerfile-oci-ta
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-push-dockerfile-oci-ta:0.1@sha256:5d8013b6a27bbc5e4ff261144616268f28417ed0950d583ef36349fcd59d3d3d
+        value: quay.io/konflux-ci/tekton-catalog/task-push-dockerfile-oci-ta:0.1@sha256:8c75c4a747e635e5f3e12266a3bb6e5d3132bf54e37eaa53d505f89897dd8eca
      - name: kind
        value: task
      resolver: bundles
@ -631,7 +629,7 @@ spec:
      - name: name
        value: show-sbom
      - name: bundle
-        value: quay.io/konflux-ci/tekton-catalog/task-show-sbom:0.1@sha256:1b1df4da95966d08ac6a5b8198710e09e68b5c2cdc707c37d9d19769e65884b2
+        value: quay.io/konflux-ci/tekton-catalog/task-show-sbom:0.1@sha256:86c069cac0a669797e8049faa8aa4088e70ff7fcd579d5bdc37626a9e0488a05
      - name: kind
        value: task
      resolver: bundles
--- a/.tekton/ramalama-cli/ramalama-cli-pull-request.yaml
+++ b/.tekton/ramalama-cli/ramalama-cli-pull-request.yaml
@ -0,0 +1,42 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/pull_request_number: '{{pull_request_number}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "true"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: ramalama-cli
+    pipelines.appstudio.openshift.io/type: build
+  name: ramalama-cli-on-pull-request
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/ramalama-cli:on-pr-{{revision}}
+  - name: image-expires-after
+    value: 5d
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
+  - name: dockerfile
+    value: container-images/ramalama-cli/Containerfile
+  pipelineRef:
+    name: pull-request-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/ramalama-cli/ramalama-cli-push.yaml
+++ b/.tekton/ramalama-cli/ramalama-cli-push.yaml
@ -0,0 +1,39 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  annotations:
+    build.appstudio.openshift.io/repo: https://github.com/containers/ramalama?rev={{revision}}
+    build.appstudio.redhat.com/commit_sha: '{{revision}}'
+    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
+    pipelinesascode.tekton.dev/cancel-in-progress: "false"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
+  labels:
+    appstudio.openshift.io/application: ramalama
+    appstudio.openshift.io/component: ramalama-cli
+    pipelines.appstudio.openshift.io/type: build
+  name: ramalama-cli-on-push
+  namespace: ramalama-tenant
+spec:
+  params:
+  - name: git-url
+    value: '{{source_url}}'
+  - name: revision
+    value: '{{revision}}'
+  - name: output-image
+    value: quay.io/redhat-user-workloads/ramalama-tenant/ramalama-cli:{{revision}}
+  - name: build-platforms
+    value:
+    - linux-c4xlarge/amd64
+    - linux-c4xlarge/arm64
+  - name: dockerfile
+    value: container-images/ramalama-cli/Containerfile
+  pipelineRef:
+    name: push-pipeline
+  timeouts:
+    pipeline: 6h
+  workspaces:
+  - name: git-auth
+    secret:
+      secretName: '{{ git_auth_secret }}'
--- a/.tekton/ramalama-llama-server/ramalama-llama-server-pull-request.yaml
+++ b/.tekton/ramalama-llama-server/ramalama-llama-server-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: ramalama-llama-server
--- a/.tekton/ramalama-llama-server/ramalama-llama-server-push.yaml
+++ b/.tekton/ramalama-llama-server/ramalama-llama-server-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: ramalama-llama-server
--- a/.tekton/ramalama-rag/ramalama-rag-pull-request.yaml
+++ b/.tekton/ramalama-rag/ramalama-rag-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: ramalama-rag
--- a/.tekton/ramalama-rag/ramalama-rag-push.yaml
+++ b/.tekton/ramalama-rag/ramalama-rag-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: ramalama-rag
--- a/.tekton/ramalama-whisper-server/ramalama-whisper-server-pull-request.yaml
+++ b/.tekton/ramalama-whisper-server/ramalama-whisper-server-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: ramalama-whisper-server
--- a/.tekton/ramalama-whisper-server/ramalama-whisper-server-push.yaml
+++ b/.tekton/ramalama-whisper-server/ramalama-whisper-server-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: ramalama-whisper-server
--- a/.tekton/ramalama/ramalama-pull-request.yaml
+++ b/.tekton/ramalama/ramalama-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: ramalama
--- a/.tekton/ramalama/ramalama-push.yaml
+++ b/.tekton/ramalama/ramalama-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: ramalama
--- a/.tekton/rocm-llama-server/rocm-llama-server-pull-request.yaml
+++ b/.tekton/rocm-llama-server/rocm-llama-server-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-llama-server
--- a/.tekton/rocm-llama-server/rocm-llama-server-push.yaml
+++ b/.tekton/rocm-llama-server/rocm-llama-server-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-llama-server
--- a/.tekton/rocm-rag/rocm-rag-pull-request.yaml
+++ b/.tekton/rocm-rag/rocm-rag-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-rag
--- a/.tekton/rocm-rag/rocm-rag-push.yaml
+++ b/.tekton/rocm-rag/rocm-rag-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-rag
--- a/.tekton/rocm-ubi-llama-server/rocm-ubi-llama-server-pull-request.yaml
+++ b/.tekton/rocm-ubi-llama-server/rocm-ubi-llama-server-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-ubi-llama-server
--- a/.tekton/rocm-ubi-llama-server/rocm-ubi-llama-server-push.yaml
+++ b/.tekton/rocm-ubi-llama-server/rocm-ubi-llama-server-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-ubi-llama-server
--- a/.tekton/rocm-ubi-rag/rocm-ubi-rag-pull-request.yaml
+++ b/.tekton/rocm-ubi-rag/rocm-ubi-rag-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-ubi-rag
--- a/.tekton/rocm-ubi-rag/rocm-ubi-rag-push.yaml
+++ b/.tekton/rocm-ubi-rag/rocm-ubi-rag-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-ubi-rag
--- a/.tekton/rocm-ubi-whisper-server/rocm-ubi-whisper-server-pull-request.yaml
+++ b/.tekton/rocm-ubi-whisper-server/rocm-ubi-whisper-server-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-ubi-whisper-server
--- a/.tekton/rocm-ubi-whisper-server/rocm-ubi-whisper-server-push.yaml
+++ b/.tekton/rocm-ubi-whisper-server/rocm-ubi-whisper-server-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-ubi-whisper-server
--- a/.tekton/rocm-ubi/rocm-ubi-pull-request.yaml
+++ b/.tekton/rocm-ubi/rocm-ubi-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-ubi
--- a/.tekton/rocm-ubi/rocm-ubi-push.yaml
+++ b/.tekton/rocm-ubi/rocm-ubi-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-ubi
--- a/.tekton/rocm-whisper-server/rocm-whisper-server-pull-request.yaml
+++ b/.tekton/rocm-whisper-server/rocm-whisper-server-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-whisper-server
--- a/.tekton/rocm-whisper-server/rocm-whisper-server-push.yaml
+++ b/.tekton/rocm-whisper-server/rocm-whisper-server-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm-whisper-server
--- a/.tekton/rocm/rocm-pull-request.yaml
+++ b/.tekton/rocm/rocm-pull-request.yaml
@ -8,8 +8,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "true"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "pull_request" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "pull_request" && target_branch == "main" && body.action != "ready_for_review"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm
--- a/.tekton/rocm/rocm-push.yaml
+++ b/.tekton/rocm/rocm-push.yaml
@ -7,8 +7,8 @@ metadata:
    build.appstudio.redhat.com/target_branch: '{{target_branch}}'
    pipelinesascode.tekton.dev/cancel-in-progress: "false"
    pipelinesascode.tekton.dev/max-keep-runs: "3"
-    pipelinesascode.tekton.dev/on-cel-expression: event == "push" && target_branch
-      == "main"
+    pipelinesascode.tekton.dev/on-cel-expression: >-
+      event == "push" && target_branch == "main"
  labels:
    appstudio.openshift.io/application: ramalama
    appstudio.openshift.io/component: rocm
--- a/.tekton/tasks/test-cmd.yaml
+++ b/.tekton/tasks/test-cmd.yaml
@ -7,58 +7,29 @@ spec:
  params:
  - name: image
    description: The image to use when setting up the test environment.
-  - name: source-artifact
-    description: The Trusted Artifact URI pointing to the artifact with the application source code.
  - name: cmd
    description: The command to run.
  - name: envs
    description: List of environment variables (NAME=VALUE) to be set in the test environment.
    type: array
    default: []
-  volumes:
-  - name: workdir
-    emptyDir: {}
-  stepTemplate:
-    volumeMounts:
-    - mountPath: /var/workdir
-      name: workdir
+  steps:
+  - name: run
+    image: $(params.image)
    computeResources:
      limits:
        memory: 4Gi
      requests:
        cpu: "1"
        memory: 1Gi
-  steps:
-  - name: use-trusted-artifact
-    image: quay.io/konflux-ci/build-trusted-artifacts:latest@sha256:4689f88dd253bd1feebf57f1a76a5a751880f739000719cd662bbdc76990a7fd
-    args:
-    - use
-    - $(params.source-artifact)=/var/workdir/source
-  - name: set-env
-    image: $(params.image)
-    workingDir: /var/workdir/source
-    args:
-    - $(params.envs[*])
-    script: |
-      #!/bin/bash -e
-      rm -f .bashenv
-      while [ $# -ne 0 ]; do
-        echo "$1" >> .bashenv
-        shift
-      done
-  - name: run
-    image: $(params.image)
    securityContext:
      capabilities:
        add:
        - SETFCAP
-    workingDir: /var/workdir/source
-    env:
-    - name: BASH_ENV
-      value: .bashenv
    command:
    - /usr/bin/entrypoint.sh
    args:
+    - $(params.envs[*])
    - /bin/bash
    - -ex
    - -c
--- a/2
+++ b/2
@ -168,7 +168,7 @@ bats-image:
 	podman inspect $(BATS_IMAGE) &> /dev/null || \
 		podman build -t $(BATS_IMAGE) -f container-images/bats/Containerfile .

-bats-in-container: extra-opts = --security-opt unmask=/proc/* --device /dev/net/tun
+bats-in-container: extra-opts = --security-opt unmask=/proc/* --device /dev/net/tun --device /dev/fuse

 %-in-container: bats-image
 	podman run -it --rm \
--- a/README.md
+++ b/README.md
@ -2,14 +2,12 @@
 <img src="https://github.com/user-attachments/assets/1a338ecf-dc84-4495-8c70-16882955da47" width=50%>
 </p>

-[RamaLama](https://ramalama.ai) is an open-source tool that simplifies the local use and serving of AI models for inference from any source through the familiar approach of containers.
+[RamaLama](https://ramalama.ai) strives to make working with AI simple, straightforward, and familiar by using OCI containers.
 <br>
 <br>

 ## Description
-RamaLama strives to make working with AI simple, straightforward, and familiar by using OCI containers.
-
-RamaLama is an open-source tool that simplifies the local use and serving of AI models for inference from any source through the familiar approach of containers. Using a container engine like Podman, engineers can use container-centric development patterns and benefits to extend to AI use cases.
+RamaLama is an open-source tool that simplifies the local use and serving of AI models for inference from any source through the familiar approach of containers. It allows engineers to use container-centric development patterns and benefits to extend to AI use cases.

 RamaLama eliminates the need to configure the host system by instead pulling a container image specific to the GPUs discovered on the host system, and allowing you to work with various models and platforms.

@ -23,6 +21,25 @@ RamaLama eliminates the need to configure the host system by instead pulling a c
 - Interact with models via REST API or as a chatbot.
 <br>

+## Install
+### Install on Fedora
+RamaLama is available in [Fedora](https://fedoraproject.org/) and later. To install it, run:
+```
+sudo dnf install python3-ramalama
+```
+
+### Install via PyPI
+RamaLama is available via PyPI at [https://pypi.org/project/ramalama](https://pypi.org/project/ramalama)
+```
+pip install ramalama
+```
+
+### Install script (Linux and macOS)
+Install RamaLama by running:
+```
+curl -fsSL https://ramalama.ai/install.sh | bash
+```
+
 ## Accelerated images

 | Accelerator                       | Image                      |
@ -103,25 +120,6 @@ pip install mlx-lm
 ramalama --runtime=mlx serve hf://mlx-community/Unsloth-Phi-4-4bit
 ```

-## Install
-### Install on Fedora
-RamaLama is available in [Fedora 40](https://fedoraproject.org/) and later. To install it, run:
-```
-sudo dnf install ramalama
-```
-
-### Install via PyPi
-RamaLama is available via PyPi at [https://pypi.org/project/ramalama](https://pypi.org/project/ramalama)
-```
-pip install ramalama
-```
-
-### Install script (Linux and macOS)
-Install RamaLama by running:
-```
-curl -fsSL https://ramalama.ai/install.sh | bash
-```
-
 #### Default Container Engine
 When both Podman and Docker are installed, RamaLama defaults to Podman. The `RAMALAMA_CONTAINER_ENGINE=docker` environment variable can override this behaviour. When neither are installed, RamaLama will attempt to run the model with software on the local system.
 <br>
--- a/container-images/bats/Containerfile
+++ b/container-images/bats/Containerfile
@ -1,12 +1,11 @@
 FROM quay.io/fedora/fedora:42

 ENV HOME=/tmp \
-    XDG_RUNTIME_DIR=/tmp \
-    STORAGE_DRIVER=vfs
+    XDG_RUNTIME_DIR=/tmp
 WORKDIR /src
 ENTRYPOINT ["/usr/bin/entrypoint.sh"]

-RUN dnf -y install make bats jq iproute podman openssl httpd-tools \
+RUN dnf -y install make bats jq iproute podman openssl httpd-tools diffutils \
    python3-huggingface-hub \
    $([ $(uname -m) == "x86_64" ] && echo ollama) \
    # for validate and unit-tests
@ -26,4 +25,6 @@ RUN git clone --depth=1 https://github.com/ggml-org/llama.cpp && \

 COPY container-images/bats/entrypoint.sh /usr/bin
 COPY container-images/bats/containers.conf /etc/containers
+COPY . /src
+RUN chmod -R a+rw /src
 RUN chmod a+rw /etc/subuid /etc/subgid
--- a/container-images/bats/entrypoint.sh
+++ b/container-images/bats/entrypoint.sh
@ -3,6 +3,16 @@
 echo "$(id -un):10000:2000" > /etc/subuid
 echo "$(id -un):10000:2000" > /etc/subgid

+while [ $# -gt 0 ]; do
+    if [[ "$1" =~ = ]]; then
+        # shellcheck disable=SC2163
+        export "$1"
+        shift
+    else
+        break
+    fi
+done
+
 if [ $# -gt 0 ]; then
    exec "$@"
 else
--- a/container-images/openvino/Containerfile
+++ b/container-images/openvino/Containerfile
@ -1,4 +1,4 @@
-FROM registry.access.redhat.com/ubi9/ubi:9.6-1752069608
+FROM registry.access.redhat.com/ubi9/ubi:9.6-1752625787

 # Install Python development dependencies
 RUN dnf install -y python3-devel wget compat-openssl11 python3-jinja2 python3-markupsafe
--- a/container-images/ramalama-vllm/Containerfile
+++ b/container-images/ramalama-vllm/Containerfile
@ -0,0 +1,17 @@
+FROM quay.io/ramalama/ramalama
+
+ENV PATH="/root/.local/bin:$PATH"
+ENV VIRTUAL_ENV="/opt/venv"
+ENV UV_PYTHON_INSTALL_DIR="/opt/uv/python"
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+ENV UV_HTTP_TIMEOUT=500
+
+ENV UV_INDEX_STRATEGY="unsafe-best-match"
+ENV UV_LINK_MODE="copy"
+
+COPY . /src/ramalama
+WORKDIR /src/ramalama
+RUN container-images/scripts/build-vllm.sh
+WORKDIR /
+
--- a/container-images/rocm-ubi/Containerfile
+++ b/container-images/rocm-ubi/Containerfile
@ -1,4 +1,4 @@
-FROM registry.access.redhat.com/ubi9/ubi:9.6-1752069608
+FROM registry.access.redhat.com/ubi9/ubi:9.6-1752625787

 COPY container-images/rocm-ubi/amdgpu.repo /etc/yum.repos.d/
 COPY container-images/rocm-ubi/rocm.repo /etc/yum.repos.d/
--- a/container-images/scripts/build-vllm.sh
+++ b/container-images/scripts/build-vllm.sh
@ -0,0 +1,90 @@
+#!/bin/bash
+
+available() {
+  command -v "$1" >/dev/null
+}
+
+install_deps() {
+  set -eux -o pipefail
+
+  if available dnf; then
+    dnf install -y git curl wget ca-certificates gcc gcc-c++ \
+      gperftools-libs numactl-devel ffmpeg libSM libXext mesa-libGL jq lsof \
+      vim numactl
+    dnf -y clean all
+    rm -rf /var/cache/*dnf*
+  elif available apt-get; then
+    apt-get update -y
+    apt-get install -y --no-install-recommends git curl wget ca-certificates \
+      gcc g++ libtcmalloc-minimal4 libnuma-dev ffmpeg libsm6 libxext6 libgl1 \
+      jq lsof vim numactl
+    rm -rf /var/lib/apt/lists/*
+  fi
+
+  curl -LsSf https://astral.sh/uv/0.7.21/install.sh | bash
+}
+
+preload_and_ulimit() {
+  local ld_preload_file="libtcmalloc_minimal.so.4"
+  local ld_preload_file_1="/usr/lib/$arch-linux-gnu/$ld_preload_file"
+  local ld_preload_file_2="/usr/lib64/$ld_preload_file"
+  if [ -e "$ld_preload_file_1" ]; then
+    ld_preload_file="$ld_preload_file_1"
+  elif [ -e "$ld_preload_file_2" ]; then
+    ld_preload_file="$ld_preload_file_2"
+  fi
+
+  if [ -e "$ld_preload_file" ]; then
+    echo "LD_PRELOAD=$ld_preload_file" >> /etc/environment
+  fi
+
+  echo 'ulimit -c 0' >> ~/.bashrc
+}
+
+pip_install() {
+  local url="https://download.pytorch.org/whl/cpu"
+  uv pip install -v -r "$1" --extra-index-url $url
+}
+
+git_clone_specific_commit() {
+  local repo="${vllm_url##*/}"
+  git init "$repo"
+  cd "$repo"
+  git remote add origin "$vllm_url"
+  git fetch --depth 1 origin $commit
+  git reset --hard $commit
+}
+
+main() {
+  set -eux -o pipefail
+
+  install_deps
+
+  local arch
+  arch=$(uname -m)
+  preload_and_ulimit
+
+  uv venv --python 3.12 --seed "$VIRTUAL_ENV"
+  uv pip install --upgrade pip
+
+  local vllm_url="https://github.com/vllm-project/vllm"
+  local commit="ac9fb732a5c0b8e671f8c91be8b40148282bb14a"
+  git_clone_specific_commit
+  if [ "$arch" == "x86_64" ]; then
+    export VLLM_CPU_DISABLE_AVX512="0"
+    export VLLM_CPU_AVX512BF16="0"
+    export VLLM_CPU_AVX512VNNI="0"
+  elif [ "$arch" == "aarch64" ]; then
+    export VLLM_CPU_DISABLE_AVX512="true"
+  fi
+
+  pip_install requirements/cpu-build.txt
+  pip_install requirements/cpu.txt
+
+  MAX_JOBS=2 VLLM_TARGET_DEVICE=cpu python3 setup.py install
+  cd -
+  rm -rf vllm /root/.cache
+}
+
+main "$@"
+
--- a/container-images/scripts/build_llama_and_whisper.sh
+++ b/container-images/scripts/build_llama_and_whisper.sh
@ -99,10 +99,10 @@ is_rhel_based() { # doesn't include openEuler
 dnf_install_mesa() {
  if [ "${ID}" = "fedora" ]; then
    dnf copr enable -y slp/mesa-libkrun-vulkan
-    dnf install -y mesa-vulkan-drivers-25.0.7-100.fc42 "${vulkan_rpms[@]}"
+    dnf install -y mesa-vulkan-drivers-25.0.7-100.fc42 virglrenderer "${vulkan_rpms[@]}"
    dnf versionlock add mesa-vulkan-drivers-25.0.7-100.fc42
  else
-    dnf install -y mesa-vulkan-drivers "${vulkan_rpms[@]}"
+    dnf install -y mesa-vulkan-drivers virglrenderer "${vulkan_rpms[@]}"
  fi

  rm_non_ubi_repos
--- a/container-images/scripts/build_rag.sh
+++ b/container-images/scripts/build_rag.sh
@ -40,7 +40,18 @@ update_python() {
 }

 docling() {
-    ${python} -m pip install --prefix=/usr docling docling-core accelerate --extra-index-url https://download.pytorch.org/whl/"$1"
+    case $1 in
+        cuda)
+            PYTORCH_DIR="cu128"
+            ;;
+        rocm)
+            PYTORCH_DIR="rocm6.3"
+            ;;
+        *)
+            PYTORCH_DIR="cpu"
+            ;;
+    esac
+    ${python} -m pip install --prefix=/usr docling docling-core accelerate --extra-index-url "https://download.pytorch.org/whl/$PYTORCH_DIR"
    # Preloads models (assumes its installed from container_build.sh)
    doc2rag load
 }
@ -51,6 +62,8 @@ rag() {
 }

 to_gguf() {
+    # required to build under GCC 15 until a new release is available, see https://github.com/google/sentencepiece/issues/1108 for details
+    export CXXFLAGS="-include cstdint"
    ${python} -m pip install --prefix=/usr "numpy~=1.26.4" "sentencepiece~=0.2.0" "transformers>=4.45.1,<5.0.0" git+https://github.com/ggml-org/llama.cpp#subdirectory=gguf-py "protobuf>=4.21.0,<5.0.0"
 }

@ -60,6 +73,9 @@ main() {
    # shellcheck disable=SC1091
    source /etc/os-release

+    # caching in a container build is unhelpful, and can cause errors
+    export PIP_NO_CACHE_DIR=1
+
    local arch
    arch="$(uname -m)"
    local gpu="${1-cpu}"
@ -67,18 +83,14 @@ main() {
    python=$(python_version)
    local pkgs
    if available dnf; then
-        pkgs=("git-core" "gcc" "gcc-c++")
+        pkgs=("git-core" "gcc" "gcc-c++" "cmake")
    else
-        pkgs=("git" "gcc" "g++")
+        pkgs=("git" "gcc" "g++" "cmake")
    fi
    if [ "${gpu}" = "cuda" ]; then
        pkgs+=("libcudnn9-devel-cuda-12" "libcusparselt0" "cuda-cupti-12-*")
    fi

-    if [[ "$ID" = "fedora" && "$VERSION_ID" -ge 42 ]] ; then
-        pkgs+=("python3-sentencepiece-0.2.0")
-    fi
-
    update_python
    to_gguf

--- a/container_build.sh
+++ b/container_build.sh
@ -62,7 +62,7 @@ add_rag() {
    tag=$tag-rag
    containerfile="container-images/common/Containerfile.rag"
    GPU=cpu
-    case $2 in
+    case "${2##*/}" in
 	cuda)
 	    GPU=cuda
 	    ;;
--- a/pyproject.toml
+++ b/pyproject.toml
@ -110,7 +110,7 @@ log_cli_date_format = "%Y-%m-%d %H:%M:%S"
 include = ["ramalama", "ramalama.*"]

 [tool.setuptools.data-files]
-"share/ramalama" = ["shortnames/shortnames.conf"]
+"share/ramalama" = ["shortnames/shortnames.conf", "docs/ramalama.conf"]
 "share/man/man1" = ["docs/*.1"]
 "share/man/man5" = ["docs/*.5"]
 "share/man/man7" = ["docs/*.7"]
--- a/ramalama/cli.py
+++ b/ramalama/cli.py
@ -133,6 +133,10 @@ def get_parser():

 def init_cli():
    """Initialize the RamaLama CLI and parse command line arguments."""
+    # Need to know if we're running with --dryrun or --generate before adding the subcommands,
+    # otherwise calls to accel_image() when setting option defaults will cause unnecessary image pulls.
+    if any(arg in ("--dryrun", "--dry-run", "--generate") or arg.startswith("--generate=") for arg in sys.argv[1:]):
+        CONFIG.dryrun = True
    parser = get_parser()
    args = parse_arguments(parser)
    post_parse_setup(args)
@ -703,7 +707,7 @@ def _get_source_model(args):
    smodel = New(src, args)
    if smodel.type == "OCI":
        raise ValueError(f"converting from an OCI based image {src} is not supported")
-    if not smodel.exists():
+    if not smodel.exists() and not args.dryrun:
        smodel.pull(args)
    return smodel

@ -1004,6 +1008,8 @@ def serve_parser(subparsers):
 def _get_rag(args):
    if os.path.exists(args.rag):
        return
+    if args.pull == "never" or args.dryrun:
+        return
    model = New(args.rag, args=args, transport="oci")
    if not model.exists():
        model.pull(args)
--- a/ramalama/common.py
+++ b/ramalama/common.py
@ -127,7 +127,7 @@ def exec_cmd(args, stdout2null: bool = False, stderr2null: bool = False):
        raise


-def run_cmd(args, cwd=None, stdout=subprocess.PIPE, ignore_stderr=False, ignore_all=False):
+def run_cmd(args, cwd=None, stdout=subprocess.PIPE, ignore_stderr=False, ignore_all=False, encoding=None):
    """
    Run the given command arguments.

@ -137,6 +137,7 @@ def run_cmd(args, cwd=None, stdout=subprocess.PIPE, ignore_stderr=False, ignore_
    stdout: standard output configuration
    ignore_stderr: if True, ignore standard error
    ignore_all: if True, ignore both standard output and standard error
+    encoding: encoding to apply to the result text
    """
    logger.debug(f"run_cmd: {quoted(args)}")
    logger.debug(f"Working directory: {cwd}")
@ -151,7 +152,7 @@ def run_cmd(args, cwd=None, stdout=subprocess.PIPE, ignore_stderr=False, ignore_
    if ignore_all:
        sout = subprocess.DEVNULL

-    result = subprocess.run(args, check=True, cwd=cwd, stdout=sout, stderr=serr)
+    result = subprocess.run(args, check=True, cwd=cwd, stdout=sout, stderr=serr, encoding=encoding)
    logger.debug(f"Command finished with return code: {result.returncode}")

    return result
@ -225,34 +226,72 @@ def engine_version(engine: SUPPORTED_ENGINES) -> str:
    return run_cmd(cmd_args).stdout.decode("utf-8").strip()


-def resolve_cdi(spec_dirs: List[str]):
-    """Loads all CDI specs from the given directories."""
-    for spec_dir in spec_dirs:
-        for root, _, files in os.walk(spec_dir):
-            for file in files:
-                if file.endswith('.json') or file.endswith('.yaml'):
-                    if load_spec(os.path.join(root, file)):
-                        return True
+def load_cdi_yaml(stream) -> dict:
+    # Returns a dict containing just the "devices" key, whose value is
+    # a list of dicts, each mapping the key "name" to a device name.
+    # For example: {'devices': [{'name': 'all'}]}
+    # This depends on the key "name" being unique to the list of dicts
+    # under "devices" and the value of the "name" key being on the
+    # same line following a colon.

-    return False
-
-
-def yaml_safe_load(stream) -> dict:
-    data = {}
+    data = {"devices": []}
    for line in stream:
        if ':' in line:
            key, value = line.split(':', 1)
-            data[key.strip()] = value.strip()
-
+            if key.strip() == "name":
+                data['devices'].append({'name': value.strip().strip('"')})
    return data


-def load_spec(path: str):
-    """Loads a single CDI spec file."""
-    with open(path, 'r') as f:
-        spec = json.load(f) if path.endswith('.json') else yaml_safe_load(f)
+def load_cdi_config(spec_dirs: List[str]) -> dict | None:
+    # Loads the first YAML or JSON CDI configuration file found in the
+    # given directories."""

-    return spec.get('kind')
+    for spec_dir in spec_dirs:
+        for root, _, files in os.walk(spec_dir):
+            for file in files:
+                _, ext = os.path.splitext(file)
+                file_path = os.path.join(root, file)
+                if ext in [".yaml", ".yml"]:
+                    try:
+                        with open(file_path, "r") as stream:
+                            return load_cdi_yaml(stream)
+                    except OSError:
+                        continue
+                elif ext == ".json":
+                    try:
+                        with open(file_path, "r") as stream:
+                            return json.load(stream)
+                    except json.JSONDecodeError:
+                        continue
+                    except UnicodeDecodeError:
+                        continue
+                    except OSError:
+                        continue
+    return None
+
+
+def find_in_cdi(devices: List[str]) -> tuple[List[str], List[str]]:
+    # Attempts to find a CDI configuration for each device in devices
+    # and returns a list of configured devices and a list of
+    # unconfigured devices.
+    cdi = load_cdi_config(['/etc/cdi', '/var/run/cdi'])
+    cdi_devices = cdi.get("devices", []) if cdi else []
+    cdi_device_names = [name for cdi_device in cdi_devices if (name := cdi_device.get("name"))]
+
+    configured = []
+    unconfigured = []
+    for device in devices:
+        if device in cdi_device_names:
+            configured.append(device)
+        # A device can be specified by a prefix of the uuid
+        elif device.startswith("GPU") and any(name.startswith(device) for name in cdi_device_names):
+            configured.append(device)
+        else:
+            perror(f"Device {device} does not have a CDI configuration")
+            unconfigured.append(device)
+
+    return configured, unconfigured


 def check_asahi() -> Literal["asahi"] | None:
@ -278,27 +317,41 @@ def check_metal(args: ContainerArgType) -> bool:
@lru_cache(maxsize=1)
 def check_nvidia() -> Literal["cuda"] | None:
    try:
-        command = ['nvidia-smi']
-        run_cmd(command).stdout.decode("utf-8")
+        command = ['nvidia-smi', '--query-gpu=index,uuid', '--format=csv,noheader']
+        result = run_cmd(command, encoding="utf-8")
+    except OSError:
+        return None

-        # ensure at least one CDI device resolves
-        if resolve_cdi(['/etc/cdi', '/var/run/cdi']):
-            if "CUDA_VISIBLE_DEVICES" not in os.environ:
-                dev_command = ['nvidia-smi', '--query-gpu=index', '--format=csv,noheader']
-                try:
-                    result = run_cmd(dev_command)
-                    output = result.stdout.decode("utf-8").strip()
-                    if not output:
-                        raise ValueError("nvidia-smi returned empty GPU indices")
-                    devices = ','.join(output.split('\n'))
-                except Exception:
-                    devices = "0"
+    smi_lines = result.stdout.splitlines()
+    parsed_lines = [[item.strip() for item in line.split(',')] for line in smi_lines if line]
+    if not parsed_lines:
+        return None

-                os.environ["CUDA_VISIBLE_DEVICES"] = devices
+    indices, uuids = zip(*parsed_lines) if parsed_lines else (tuple(), tuple())
+    # Get the list of devices specified by CUDA_VISIBLE_DEVICES, if any
+    cuda_visible_devices = os.environ.get("CUDA_VISIBLE_DEVICES", "")
+    visible_devices = cuda_visible_devices.split(',') if cuda_visible_devices else []
+    for device in visible_devices:
+        if device not in indices and not any(uuid.startswith(device) for uuid in uuids):
+            perror(f"{device} not found")
+            return None

-            return "cuda"
-    except Exception:
-        pass
+    configured, unconfigured = find_in_cdi(visible_devices + ["all"])
+
+    if unconfigured and "all" not in configured:
+        perror(f"No CDI configuration found for {','.join(unconfigured)}")
+        perror("You can use the \"nvidia-ctk cdi generate\" command from the ")
+        perror("nvidia-container-toolkit to generate a CDI configuration.")
+        perror("See ramalama-cuda(7).")
+        return None
+    elif configured:
+        if "all" in configured:
+            configured.remove("all")
+            if not configured:
+                configured = indices
+
+        os.environ["CUDA_VISIBLE_DEVICES"] = ','.join(configured)
+        return "cuda"

    return None

@ -350,6 +403,9 @@ def check_intel() -> Literal["intel"] | None:
    intel_gpus = (
        b"0xe20b",
        b"0xe20c",
+        b"0x46a6",
+        b"0x46a8",
+        b"0x46aa",
        b"0x56a0",
        b"0x56a1",
        b"0x7d51",
@ -566,7 +622,7 @@ def accel_image(config: Config) -> str:

    vers = minor_release()

-    should_pull = config.pull in ["always", "missing"]
+    should_pull = config.pull in ["always", "missing"] and not config.dryrun
    if attempt_to_use_versioned(config.engine, image, vers, True, should_pull):
        return f"{image}:{vers}"

--- a/ramalama/config.py
+++ b/ramalama/config.py
@ -98,6 +98,7 @@ class BaseConfig:
    default_image: str = DEFAULT_IMAGE
    user: UserConfig = field(default_factory=UserConfig)
    selinux: bool = False
+    dryrun: bool = False
    settings: RamalamaSettings = field(default_factory=RamalamaSettings)

    def __post_init__(self):
--- a/ramalama/engine.py
+++ b/ramalama/engine.py
@ -216,7 +216,11 @@ def containers(args):

    conman_args = [conman, "ps", "-a", "--filter", "label=ai.ramalama"]
    if getattr(args, "noheading", False):
-        conman_args += ["--noheading"]
+        if conman == "docker" and not args.format:
+            # implement --noheading by using --format
+            conman_args += ["--format={{.ID}} {{.Image}} {{.Command}} {{.CreatedAt}} {{.Status}} {{.Ports}} {{.Names}}"]
+        else:
+            conman_args += ["--noheading"]

    if getattr(args, "notrunc", False):
        conman_args += ["--no-trunc"]
--- a/ramalama/huggingface.py
+++ b/ramalama/huggingface.py
@ -15,7 +15,7 @@ from ramalama.model_store.snapshot_file import SnapshotFileType

 missing_huggingface = """
 Optional: Huggingface models require the huggingface-cli module.
-This module can be installed via PyPi tools like uv, pip, pip3, pipx, or via
+This module can be installed via PyPI tools like uv, pip, pip3, pipx, or via
 distribution package managers like dnf or apt. Example:
 uv pip install huggingface_hub
 """
--- a/ramalama/modelscope.py
+++ b/ramalama/modelscope.py
@ -12,7 +12,7 @@ from ramalama.model_store.snapshot_file import SnapshotFileType

 missing_modelscope = """
 Optional: ModelScope models require the modelscope module.
-This module can be installed via PyPi tools like uv, pip, pip3, pipx, or via
+This module can be installed via PyPI tools like uv, pip, pip3, pipx, or via
 distribution package managers like dnf or apt. Example:
 uv pip install modelscope
 """
--- a/rpm/ramalama.spec
+++ b/rpm/ramalama.spec
@ -31,9 +31,10 @@ BuildRequires:    make
 BuildRequires:    python3-devel
 BuildRequires:    podman
 BuildRequires:    python3-pytest
+BuildRequires:    mailcap

 Provides: python3-ramalama = %{version}-%{release}
-Obsoletes: python3-ramalama < 0.10.1-2
+Obsoletes: python3-ramalama < 0.11.0-1

 Requires: podman

@ -55,14 +56,12 @@ will run the AI Models within a container based on the OCI image.
 %forgeautosetup -p1

 %build
+make docs
 %pyproject_wheel
-%{__make} docs

 %install
 %pyproject_install
 %pyproject_save_files -l %{pypi_name}
-%{__make} DESTDIR=%{buildroot} PREFIX=%{_prefix} install-docs install-shortnames
-%{__make} DESTDIR=%{buildroot} PREFIX=%{_prefix} install-completions

 %check
 %pytest -v test/unit
--- a/shortnames/shortnames.conf
+++ b/shortnames/shortnames.conf
@ -34,9 +34,9 @@
  "merlinite-lab:7b" = "huggingface://instructlab/merlinite-7b-lab-GGUF/merlinite-7b-lab-Q4_K_M.gguf"
  "merlinite-lab-7b" = "huggingface://instructlab/merlinite-7b-lab-GGUF/merlinite-7b-lab-Q4_K_M.gguf"
  "tiny" = "ollama://tinyllama"
-  "mistral" = "huggingface://TheBloke/Mistral-7B-Instruct-v0.2-GGUF/mistral-7b-instruct-v0.2.Q4_K_M.gguf"
-  "mistral:7b" = "huggingface://TheBloke/Mistral-7B-Instruct-v0.2-GGUF/mistral-7b-instruct-v0.2.Q4_K_M.gguf"
-  "mistral:7b-v3" = "huggingface://MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF/Mistral-7B-Instruct-v0.3.Q4_K_M.gguf"
+  "mistral" = "hf://lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf"
+  "mistral:7b" = "hf://lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf"
+  "mistral:7b-v3" = "hf://lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf"
  "mistral:7b-v2" = "huggingface://TheBloke/Mistral-7B-Instruct-v0.2-GGUF/mistral-7b-instruct-v0.2.Q4_K_M.gguf"
  "mistral:7b-v1" = "huggingface://TheBloke/Mistral-7B-Instruct-v0.1-GGUF/mistral-7b-instruct-v0.1.Q5_K_M.gguf"
  "mistral-small3.1" = "hf://bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF/mistralai_Mistral-Small-3.1-24B-Instruct-2503-IQ2_M.gguf"
--- a/test/system/030-run.bats
+++ b/test/system/030-run.bats
@ -14,7 +14,7 @@ EOF

    if is_container; then
 	run_ramalama info
-	conman=$(jq .Engine.Name <<< $output | tr -d '"' )
+	conman=$(jq -r .Engine.Name <<< $output)
 	verify_begin="${conman} run --rm"

 	run_ramalama -q --dryrun run ${MODEL}
@ -140,7 +140,7 @@ EOF
    skip_if_docker
    run_ramalama 22 run --image bogus --pull=never tiny
    is "$output" ".*Error: bogus: image not known"
-    run_ramalama 125 run --image bogus1 --rag quay.io/ramalama/testrag --pull=never tiny
+    run_ramalama 125 run --image bogus1 --rag quay.io/ramalama/rag --pull=never tiny
    is "$output" ".*Error: bogus1: image not known"
 }

@ -148,13 +148,10 @@ EOF
    skip_if_nocontainer
    skip_if_darwin
    skip_if_docker
-    run_ramalama 125 --dryrun run --rag quay.io/ramalama/rag --pull=never tiny
-    is "$output" "Error: quay.io/ramalama/rag: image not known.*"
-
-    run_ramalama --dryrun run --rag quay.io/ramalama/testrag --pull=never tiny
+    run_ramalama --dryrun run --rag quay.io/ramalama/rag --pull=never tiny
    is "$output" ".*quay.io/ramalama/.*-rag:"

-    run_ramalama --dryrun run --image quay.io/ramalama/ramalama:1.0 --rag quay.io/ramalama/testrag --pull=never tiny
+    run_ramalama --dryrun run --image quay.io/ramalama/ramalama:1.0 --rag quay.io/ramalama/rag --pull=never tiny
    is "$output" ".*quay.io/ramalama/ramalama:1.0"
 }

--- a/test/system/040-serve.bats
+++ b/test/system/040-serve.bats
@ -115,7 +115,6 @@ verify_begin=".*run --rm"
 }

@test "ramalama serve and stop" {
-    skip "Seems to cause race conditions"
    skip_if_nocontainer

    model=ollama://smollm:135m
@ -123,17 +122,15 @@ verify_begin=".*run --rm"
    container2=c_$(safename)

    run_ramalama serve --name ${container1} --detach ${model}
-    cid="$output"
-    run_ramalama info
-    conmon=$(jq .Engine <<< $output)
-
-    run -0 ${conman} inspect1 $cid

    run_ramalama ps
    is "$output" ".*${container1}" "list correct for container1"

-    run_ramalama chat --ls
-    is "$output" "ollama://smollm:135m" "list of models available correct"
+    run_ramalama ps --format '{{.Ports}}'
+    port=${output: -8:4}
+
+    run_ramalama chat --ls --url http://127.0.0.1:${port}/v1
+    is "$output" "smollm:135m" "list of models available correct"

    run_ramalama containers --noheading
    is "$output" ".*${container1}" "list correct for container1"
@ -151,7 +148,6 @@ verify_begin=".*run --rm"
 }

@test "ramalama --detach serve multiple" {
-    skip "Seems to cause race conditions"
    skip_if_nocontainer

    model=ollama://smollm:135m
@ -349,7 +345,7 @@ verify_begin=".*run --rm"
    rm /tmp/$name.yaml
 }

-@test "ramalama serve --api llama-stack --generate=kube:/tmp" {
+@test "ramalama serve --api llama-stack" {
    skip_if_docker
    skip_if_nocontainer
    model=tiny
@ -393,7 +389,7 @@ verify_begin=".*run --rm"
    run_ramalama 125 serve --image bogus --pull=never tiny
    is "$output" "Error: bogus: image not known"

-    run_ramalama 125 serve --image bogus1 --rag quay.io/ramalama/testrag --pull=never tiny
+    run_ramalama 125 serve --image bogus1 --rag quay.io/ramalama/rag --pull=never tiny
    is "$output" ".*Error: bogus1: image not known"
 }

@ -402,13 +398,10 @@ verify_begin=".*run --rm"
    skip_if_darwin
    skip_if_docker
    run_ramalama ? stop ${name}
-    run_ramalama ? --dryrun serve --rag quay.io/ramalama/rag --pull=never tiny
-    is "$output" ".*Error: quay.io/ramalama/rag: image not known"
-
-    run_ramalama --dryrun serve --rag quay.io/ramalama/testrag --pull=never tiny
+    run_ramalama --dryrun serve --rag quay.io/ramalama/rag --pull=never tiny
    is "$output" ".*quay.io/ramalama/.*-rag:"

-    run_ramalama --dryrun serve --image quay.io/ramalama/ramalama:1.0 --rag quay.io/ramalama/testrag --pull=never tiny
+    run_ramalama --dryrun serve --image quay.io/ramalama/ramalama:1.0 --rag quay.io/ramalama/rag --pull=never tiny
    is "$output" ".*quay.io/ramalama/ramalama:1.0"
 }

--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Daniel J Walsh	3f8e31a073	Merge pull request #1714 from slp/install-virglrenderer container-images: add virglrenderer to vulkan	2025-07-19 06:35:54 -04:00
Daniel J Walsh	08722738cf	Merge pull request #1718 from containers/konflux/references/main Update Konflux references	2025-07-19 06:34:54 -04:00
red-hat-konflux-kflux-prd-rh03[bot]	ab7adbb430	Update Konflux references Signed-off-by: red-hat-konflux-kflux-prd-rh03 <206760901+red-hat-konflux-kflux-prd-rh03[bot]@users.noreply.github.com>	2025-07-19 08:03:10 +00:00
Mike Bonnet	72504179fc	Merge pull request #1716 from containers/fix-sentencepiece-build build_rag.sh: install cmake	2025-07-18 10:54:06 -07:00
Mike Bonnet	dcfeee8538	build_rag.sh: install cmake cmake is required to build sentencepiece. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-18 09:17:33 -07:00
Daniel J Walsh	1d903e746c	Merge pull request #1677 from containers/vllm-cpu Add vllm to cpu inferencing Containerfile	2025-07-18 06:05:26 -04:00
Daniel J Walsh	13a22f6671	Merge pull request #1708 from containers/konflux-more-images konflux: add pipelines for asahi, cann, intel-gpu, llama-stack, musa, openvino, and ramalama-cli	2025-07-18 06:04:12 -04:00
Daniel J Walsh	1d6aa51cd7	Merge pull request #1712 from tonyjames/main Add support for Intel Iris Xe Graphics (46AA, 46A6, 46A8)	2025-07-18 06:03:34 -04:00
Tony James	50d01f177b	Add support for Intel Iris Xe Graphics (46AA, 46A6, 46A8) Signed-off-by: Tony James <3128081+tonyjames@users.noreply.github.com>	2025-07-17 18:58:07 -04:00
Eric Curtin	234134b5cc	Add vllm to cpu inferencing Containerfile To be built upon "ramalama" image Signed-off-by: Eric Curtin <ecurtin@redhat.com>	2025-07-17 21:09:20 +01:00
Daniel J Walsh	64ca9cfb4a	Merge pull request #1709 from containers/fix-cuda-gpu fix GPU selection and pytorch URL when building rag images	2025-07-17 11:31:41 -04:00
Eric Curtin	e3dda75ec6	Merge pull request #1707 from rhatdan/install README: remove duplicate statements	2025-07-17 15:57:12 +01:00
Daniel J Walsh	075df4bb87	Merge pull request #1617 from jwieleRH/check_nvidia Improve NVIDIA GPU detection.	2025-07-17 06:29:40 -04:00
Daniel J Walsh	5b46b23f2e	README: remove duplicate statements Simplify ramalama's top-level description. Remove the duplicate statements. Also make sure all references to PyPI are spelled this way. Signed-off-by: Ken Dreyer <kdreyer@redhat.com> Signed-off-by: Daniel J Walsh <dwalsh@redhat.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2025-07-17 06:26:55 -04:00
Daniel J Walsh	1fe1b20c8c	Merge pull request #1711 from carlwgeorge/include-config-in-wheel Included ramalama.conf in wheel	2025-07-17 06:21:47 -04:00
Mike Bonnet	f5512c8f65	build_rag.sh: install sentencepiece via pip python3-sentencepiece was pulling in an older version of protobuf. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-16 23:27:54 -07:00
Mike Bonnet	7132d5a7f8	build_rag.sh: disable pip cache pip's caching behavior was causing errors when downloading huge (4.5G) torch wheels during the rocm-ubi-rag build. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-16 23:27:54 -07:00
Mike Bonnet	2d3f8dfe28	fix GPU selection and pytorch URL when building rag images A previous commit changed the second argument to add_rag() from the image name to the full repo path. Update the case statement accordingly, so the "GPU" variable is set correctly. The "cuda" directory is no longer available on download.pytorch.org. When building for cuda, pull wheels from the "cu128" directory, which contains binaries built for CUDA 12.8. When building rocm* images, download binaries from the "rocm6.3" directory, which are built for ROCm 6.3. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-16 23:27:54 -07:00
Carl George	1d8a2e5b6c	Included ramalama.conf in wheel Currently other data files such as shortnames.conf, man pages, and shell completions are included in the Python wheel. Including ramalama.conf as well means we can avoid several calls to make in the RPM spec file, instead relying on the wheel mechanisms to put these files in place. As long as `make docs` is run before the wheel generation, all the necessary files are included. Signed-off-by: Carl George <carlwgeorge@gmail.com>	2025-07-17 01:20:28 -05:00
Eric Curtin	42ac787686	Merge pull request #1710 from containers/konflux/mintmaker/main/registry.access.redhat.com-ubi9-ubi-9.x chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.6-1752625787	2025-07-17 01:15:43 +01:00
red-hat-konflux-kflux-prd-rh03[bot]	18c560fff6	chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.6-1752625787 Signed-off-by: red-hat-konflux-kflux-prd-rh03 <206760901+red-hat-konflux-kflux-prd-rh03[bot]@users.noreply.github.com>	2025-07-17 00:03:57 +00:00
John Wiele	ce35ccb4c3	Remove pyYAML as a dependency. Extract information directly from the CDI YAML file by making some simplifying assumptions instead of doing a complete YAML parse. Default to all devices known to nvidia-smi. Fix the signature of check_nvidia(). Remove some debug logging. Signed-off-by: John Wiele <jwiele@redhat.com>	2025-07-16 16:11:39 -04:00
John Wiele	b97177b408	Apply suggestions from code review Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> Signed-off-by: John Wiele <jwiele@redhat.com>	2025-07-16 16:08:32 -04:00
John Wiele	14c4aaca39	Improve NVIDIA GPU detection. Allow GPUs to be specified by UUID as well as index since the index is not guaranteed to persist across reboots. Crosscheck requested GPUs with nvidia-smi and CDI configuration. If any requested GPUs lack corresponding CDI configuration, print a message with a pointer to documentation. If the only GPU specified in the CDI configuration is "all", as appears to be the case on WSL2, use "all" as the default. Add an optional encoding argument to run_cmd() to facilitate checking the output of the command. Add pyYAML as a dependency for parsing the CDI configuration. Signed-off-by: John Wiele <jwiele@redhat.com>	2025-07-16 16:08:32 -04:00
Mike Bonnet	bf4fd56106	konflux: add pipelines for asahi, cann, intel-gpu, llama-stack, musa, openvino, and ramalama-cli Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-16 12:23:12 -07:00
Mike Bonnet	1373a8e7ba	konflux: don't trigger pipelines on PR transition to "Ready for Review" By default, Konflux triggers new pipelines when a PR moves from Draft to "Ready for Review". Because the commit SHA hasn't changed, no new builds are performed. However, a new integration test is also triggered, and because no builds were performed it is unable to find the URL and digest of the images, causing the integration test to fail. Updating the "on-cel-expression" to exclude the transition to "Ready to Review" avoids the unnecessary pipelines and the false integration test failures. Update the whitespace of the "on-cel-expression" in the push pipelines for consistency. No functional change. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-16 12:11:54 -07:00
Sergio Lopez	74584d0b5e	container-images: add virglrenderer to vulkan When running in a krun-isolated container, we need "/usr/libexec/virgl_render_server" to be present in the container image to launch it before entering the microVM. Install the virglrenderer package in addition to mesa-vulkan-drivers. Signed-off-by: Sergio Lopez <slp@redhat.com>	2025-07-16 18:53:11 +02:00
Daniel J Walsh	4dea2ee02f	Merge pull request #1687 from containers/konflux-cuda-arm64 konflux: build cuda on arm64, and simplify testing	2025-07-16 12:01:45 -04:00
Mike Bonnet	069e98c095	fix unit tests to be independent of environment Setting RAMALAMA_IMAGE would cause some unit tests to fail. Make those tests independent of the calling environment. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-16 06:44:00 -07:00
Mike Bonnet	f57b8eb284	konflux: copy source into the bats image Including the source in the bats image ensures that we're always testing with the same version of the code that was used to build the images. It also eliminates the need for repeated checkouts of the repo and simplifies testing, avoiding additional volumes and artifact references. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-16 06:44:00 -07:00
Mike Bonnet	299d3b9b75	konflux: build cuda and layered images on arm64 Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-16 06:44:00 -07:00
Stephen Smoogen	683b8fb8a0	Minor fixes to rpm builds by packit and spec file. (#1704 ) * This removes epel9 from packit rules as epel9 does not currently build without many additional packages added to the distro. * This fixes a breakage in epel10 by adding mailcap as a buildrequires. Signed-off-by: Stephen Smoogen <ssmoogen@redhat.com> Co-authored-by: Stephen Smoogen <ssmoogen@redhat.com>	2025-07-16 09:37:00 -04:00
Mike Bonnet	64e22ee0aa	Merge pull request #1700 from containers/test-optimization-and-fixup reduce unnecessary image pulls during testing, and re-enable a couple tests	2025-07-15 11:34:59 -07:00
Mike Bonnet	651fc503bd	implement "ps --noheading" for docker using --format "docker ps" does not support the "--noheading" option. Use the --format option to emulate the behavior. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-15 10:32:53 -07:00
Daniel J Walsh	384cad7161	Merge pull request #1696 from containers/renovate/quay.io-konflux-ci-build-trusted-artifacts-latest chore(deps): update quay.io/konflux-ci/build-trusted-artifacts:latest docker digest to f7d0c51	2025-07-15 13:17:33 -04:00
Daniel J Walsh	3dec0d7487	Merge pull request #1699 from containers/renovate/registry.access.redhat.com-ubi9-ubi-9.x chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.6-1752587049	2025-07-15 13:16:27 -04:00
Daniel J Walsh	d7763ad1c5	Merge pull request #1698 from containers/mistral Mistral should point to lmstudio gguf	2025-07-15 13:15:11 -04:00
Mike Bonnet	b550cc97d2	bats: re-enable a couple tests, and minor cleanup Fix the "serve and stop" test by passing the correct (possibly random) port to "ramalama chat". Fix the definition of "ramalama_runtime". Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-15 09:03:49 -07:00
Mike Bonnet	927d2f992a	bats: allow the container to use the overlay driver when possible Remove the STORAGE_DRIVER env var from the container so it doesn't force use of the vfs driver in all cases. Mount /dev/fuse into the container when running locally. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-15 09:03:49 -07:00
Mike Bonnet	f176bb3926	add a dryrun field to Config, and set it early accel_image() is called to set option defaults, before options are even parsed. This can cause images to be pulled even if they will not actually be used, slowing down testing and making the cli less responsive. Set the "dryrun" option before the first call to accel_image() to avoid unnecessary image pulls. Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-15 09:03:49 -07:00
renovate[bot]	f38c736d23	chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.6-1752587049 Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-07-15 15:47:38 +00:00
Eric Curtin	fa2f485175	Mistral should point to lmstudio gguf I don't know who MaziyarPanahi is, but I know who lmstudio are Signed-off-by: Eric Curtin <ecurtin@redhat.com>	2025-07-15 15:04:54 +01:00
Mike Bonnet	f8c41b38c1	avoid unnecessary image pulls Don't pull images in _get_rag() and _get_source_model() if pull == "never" or if running with "--dryrun". Signed-off-by: Mike Bonnet <mikeb@redhat.com>	2025-07-14 14:42:21 -07:00
renovate[bot]	b7323f7972	chore(deps): update quay.io/konflux-ci/build-trusted-artifacts:latest docker digest to f7d0c51 Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-07-14 20:13:34 +00:00
Daniel J Walsh	53e38dea8f	Merge pull request #1694 from rhatdan/VERSION Bump to 0.11.0	2025-07-14 10:59:06 -04:00