Compare commits

base: vLLM:main

Branches Tags

vLLM:main

vLLM:build-flashinfer-aot-wheel

vLLM:releases/v0.10.0

vLLM:wide_ep_working_branch_2

vLLM:wide_ep_working_branch

vLLM:woosuk/remove-v0

vLLM:revert-21550-chengji/fix-ci

vLLM:test-debug-lb

vLLM:debug-logging

vLLM:woosuk/tool

vLLM:woosuk/tp-log

vLLM:woosuk/async-sched-dp

vLLM:add-nixl-transfer-time-logging

vLLM:woosuk/remove-v0-multi-step

vLLM:tms/distributed_timeout

vLLM:woosuk/deprecate-v0-neuron

vLLM:7snzwi-codex/change-default-logging-behavior

vLLM:codex/change-default-logging-behavior

vLLM:nixl-upstreaming

vLLM:deep_gemm_logs

vLLM:benchmark

vLLM:triton-configs

vLLM:tms/dp_cuda_visible_devices_fix

vLLM:fused-moe-tuning-ep

vLLM:mla_decode_any_head

vLLM:gpu_ids2

vLLM:nixl-debug-oh-fixed

vLLM:gpu-ids

vLLM:fix-doc-build

vLLM:dockerfile-nvcc-compress

vLLM:add-python-3.13

vLLM:releases/v0.9.2

vLLM:topk_id_hack

vLLM:add-utils

vLLM:minus_x

vLLM:woosuk/simple-cuda-graph

vLLM:acc-rate

vLLM:gemma3n-mm

vLLM:deep_full_cudagraph_fix

vLLM:deepep_tweaks

vLLM:woosuk/cache-model-info

vLLM:fix-precommit

vLLM:releases/v0.9.1

vLLM:mergify/houseroad/config-update

vLLM:lwilkinson/refactor-cmake

vLLM:codex/add-pandas-and-datasets-to-requirements

vLLM:fp8_ep_dp

vLLM:releases/v0.9.0

vLLM:codex/update-arch-overview-md-with-vllm-v1-details

vLLM:benchmark_serving_test

vLLM:pil_image

vLLM:low_latency_opt

vLLM:woosuk-jf

vLLM:disable-sd

vLLM:v0.8.5

vLLM:dependabot/github_actions/actions/setup-python-5.6.0

vLLM:benchmark-output

vLLM:khluu/test

vLLM:pd_scheduling

vLLM:v0.8.4

vLLM:v1_fix_profiler

vLLM:fix_use_ep

vLLM:dynamo-patch

vLLM:v0.8.3

vLLM:whisper-translate

vLLM:bench-latency

vLLM:khluu/try_moc

vLLM:sampler-env-variable

vLLM:v1-block-table-opt

vLLM:v0.8.2

vLLM:rob-fixes

vLLM:v1-sched-common

vLLM:v1-sched-interface-2

vLLM:v0.8.1

vLLM:v0.8.0

vLLM:mamba_tests

vLLM:running-deque

vLLM:bind_kv_caches

vLLM:reduce_scatter_comm

vLLM:amd-ci

vLLM:mla-support-awq-marlin

vLLM:tpu_v1_optimized

vLLM:v0.7.2-staging-branch

vLLM:full_cudagraph

vLLM:mla_cuda_graphs

vLLM:qwen25vl

vLLM:tpu_v1

vLLM:moondream2

vLLM:v1-cascade-opt

vLLM:v1-blocktable-opt

vLLM:correct-docs-cuda-version

vLLM:torch_dynamo

vLLM:optimize-prefix-caching-scheduling

vLLM:fix-hashing-partial-blocks

vLLM:jax-tpu

vLLM:v0.10.0

vLLM:v0.10.0rc2

vLLM:v0.10.0rc1

vLLM:v0.9.2

vLLM:v0.9.2rc2

vLLM:v0.9.2rc1

vLLM:v0.9.1

vLLM:v0.9.1rc2

vLLM:v0.9.1rc1

vLLM:v0.9.0.1

vLLM:v0.9.0

vLLM:v0.8.5.post1

vLLM:tags/v0.8.5

vLLM:tags/v0.8.4

vLLM:tags/v0.8.3

vLLM:v0.8.3rc1

vLLM:tags/v0.8.2

vLLM:tags/v0.8.1

vLLM:tags/v0.8.0

vLLM:v0.8.0rc2

vLLM:v0.8.0rc1

vLLM:v0.7.3

vLLM:v0.7.2

vLLM:v0.7.1

vLLM:v0.7.0

vLLM:v0.6.6.post1

vLLM:v0.6.6

vLLM:v0.6.5

vLLM:v0.6.4.post1

vLLM:v0.6.4

vLLM:v0.6.3.post1

vLLM:v0.6.3

vLLM:v0.6.2

vLLM:v0.6.1.post2

vLLM:v0.6.1.post1

vLLM:v0.6.1

vLLM:v0.6.0

vLLM:v0.5.5

vLLM:v0.5.4

vLLM:v0.5.3.post1

vLLM:v0.5.3

vLLM:v0.5.2

vLLM:v0.5.1

vLLM:v0.5.0.post1

vLLM:v0.5.0

vLLM:v0.4.3

vLLM:v0.4.2

vLLM:v0.4.1

vLLM:v0.4.0.post1

vLLM:v0.4.0

vLLM:v0.3.3

vLLM:v0.3.2

vLLM:v0.3.1

vLLM:v0.3.0

vLLM:v0.2.7

vLLM:v0.2.6

vLLM:v0.2.5

vLLM:v0.2.4

vLLM:v0.2.3

vLLM:v0.2.2

vLLM:v0.2.1.post1

vLLM:v0.2.1

vLLM:v0.2.0

vLLM:v0.1.7

vLLM:v0.1.6

vLLM:v0.1.5

vLLM:v0.1.4

vLLM:v0.1.3

vLLM:v0.1.2

vLLM:v0.1.1

vLLM:v0.1.0

vLLM:submission

...

compare: vLLM:v0.10.0rc2

Branches Tags

vLLM:main

vLLM:build-flashinfer-aot-wheel

vLLM:releases/v0.10.0

vLLM:wide_ep_working_branch_2

vLLM:wide_ep_working_branch

vLLM:woosuk/remove-v0

vLLM:revert-21550-chengji/fix-ci

vLLM:test-debug-lb

vLLM:debug-logging

vLLM:woosuk/tool

vLLM:woosuk/tp-log

vLLM:woosuk/async-sched-dp

vLLM:add-nixl-transfer-time-logging

vLLM:woosuk/remove-v0-multi-step

vLLM:tms/distributed_timeout

vLLM:woosuk/deprecate-v0-neuron

vLLM:7snzwi-codex/change-default-logging-behavior

vLLM:codex/change-default-logging-behavior

vLLM:nixl-upstreaming

vLLM:deep_gemm_logs

vLLM:benchmark

vLLM:triton-configs

vLLM:tms/dp_cuda_visible_devices_fix

vLLM:fused-moe-tuning-ep

vLLM:mla_decode_any_head

vLLM:gpu_ids2

vLLM:nixl-debug-oh-fixed

vLLM:gpu-ids

vLLM:fix-doc-build

vLLM:dockerfile-nvcc-compress

vLLM:add-python-3.13

vLLM:releases/v0.9.2

vLLM:topk_id_hack

vLLM:add-utils

vLLM:minus_x

vLLM:woosuk/simple-cuda-graph

vLLM:acc-rate

vLLM:gemma3n-mm

vLLM:deep_full_cudagraph_fix

vLLM:deepep_tweaks

vLLM:woosuk/cache-model-info

vLLM:fix-precommit

vLLM:releases/v0.9.1

vLLM:mergify/houseroad/config-update

vLLM:lwilkinson/refactor-cmake

vLLM:codex/add-pandas-and-datasets-to-requirements

vLLM:fp8_ep_dp

vLLM:releases/v0.9.0

vLLM:codex/update-arch-overview-md-with-vllm-v1-details

vLLM:benchmark_serving_test

vLLM:pil_image

vLLM:low_latency_opt

vLLM:woosuk-jf

vLLM:disable-sd

vLLM:v0.8.5

vLLM:dependabot/github_actions/actions/setup-python-5.6.0

vLLM:benchmark-output

vLLM:khluu/test

vLLM:pd_scheduling

vLLM:v0.8.4

vLLM:v1_fix_profiler

vLLM:fix_use_ep

vLLM:dynamo-patch

vLLM:v0.8.3

vLLM:whisper-translate

vLLM:bench-latency

vLLM:khluu/try_moc

vLLM:sampler-env-variable

vLLM:v1-block-table-opt

vLLM:v0.8.2

vLLM:rob-fixes

vLLM:v1-sched-common

vLLM:v1-sched-interface-2

vLLM:v0.8.1

vLLM:v0.8.0

vLLM:mamba_tests

vLLM:running-deque

vLLM:bind_kv_caches

vLLM:reduce_scatter_comm

vLLM:amd-ci

vLLM:mla-support-awq-marlin

vLLM:tpu_v1_optimized

vLLM:v0.7.2-staging-branch

vLLM:full_cudagraph

vLLM:mla_cuda_graphs

vLLM:qwen25vl

vLLM:tpu_v1

vLLM:moondream2

vLLM:v1-cascade-opt

vLLM:v1-blocktable-opt

vLLM:correct-docs-cuda-version

vLLM:torch_dynamo

vLLM:optimize-prefix-caching-scheduling

vLLM:fix-hashing-partial-blocks

vLLM:jax-tpu

vLLM:v0.10.0

vLLM:v0.10.0rc2

vLLM:v0.10.0rc1

vLLM:v0.9.2

vLLM:v0.9.2rc2

vLLM:v0.9.2rc1

vLLM:v0.9.1

vLLM:v0.9.1rc2

vLLM:v0.9.1rc1

vLLM:v0.9.0.1

vLLM:v0.9.0

vLLM:v0.8.5.post1

vLLM:tags/v0.8.5

vLLM:tags/v0.8.4

vLLM:tags/v0.8.3

vLLM:v0.8.3rc1

vLLM:tags/v0.8.2

vLLM:tags/v0.8.1

vLLM:tags/v0.8.0

vLLM:v0.8.0rc2

vLLM:v0.8.0rc1

vLLM:v0.7.3

vLLM:v0.7.2

vLLM:v0.7.1

vLLM:v0.7.0

vLLM:v0.6.6.post1

vLLM:v0.6.6

vLLM:v0.6.5

vLLM:v0.6.4.post1

vLLM:v0.6.4

vLLM:v0.6.3.post1

vLLM:v0.6.3

vLLM:v0.6.2

vLLM:v0.6.1.post2

vLLM:v0.6.1.post1

vLLM:v0.6.1

vLLM:v0.6.0

vLLM:v0.5.5

vLLM:v0.5.4

vLLM:v0.5.3.post1

vLLM:v0.5.3

vLLM:v0.5.2

vLLM:v0.5.1

vLLM:v0.5.0.post1

vLLM:v0.5.0

vLLM:v0.4.3

vLLM:v0.4.2

vLLM:v0.4.1

vLLM:v0.4.0.post1

vLLM:v0.4.0

vLLM:v0.3.3

vLLM:v0.3.2

vLLM:v0.3.1

vLLM:v0.3.0

vLLM:v0.2.7

vLLM:v0.2.6

vLLM:v0.2.5

vLLM:v0.2.4

vLLM:v0.2.3

vLLM:v0.2.2

vLLM:v0.2.1.post1

vLLM:v0.2.1

vLLM:v0.2.0

vLLM:v0.1.7

vLLM:v0.1.6

vLLM:v0.1.5

vLLM:v0.1.4

vLLM:v0.1.3

vLLM:v0.1.2

vLLM:v0.1.1

vLLM:v0.1.0

vLLM:submission

These branches are equal. There is no need to create a pull request.