vLLM
/
vllm-project.github.io
mirror of https://github.com/vllm-project/vllm-project.github.io.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
200 Commits 2 Branches 0 Tags 36 MiB
Commit Graph

200 Commits

Author SHA1 Message Date
Harry Mellor 539d26d8de Update link to Transformers backend docs 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-25 14:35:51 +01:00
youkaichao 800bfb147e
Add OpenRLHF blog (#54) 
* init

* fix

* update

* update

* update

* update

* update

* update

* update

* update

* update

* Update _posts/2025-04-18-openrlhf-vllm.md

Co-authored-by: youkaichao <youkaichao@gmail.com>

* fix

* Update _posts/2025-04-18-openrlhf-vllm.md

Co-authored-by: youkaichao <youkaichao@gmail.com>

* Update _posts/2025-04-18-openrlhf-vllm.md

Co-authored-by: youkaichao <youkaichao@gmail.com>

* fix

* update

* Update _posts/2025-04-18-openrlhf-vllm.md

Co-authored-by: youkaichao <youkaichao@gmail.com>

* update

* minor fix

Signed-off-by: youkaichao <youkaichao@gmail.com>

* minor fix

Signed-off-by: youkaichao <youkaichao@gmail.com>

* update

* update

* rename files

Signed-off-by: youkaichao <youkaichao@gmail.com>

---------

Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: jianh <jianh@nvidia.com>
Co-authored-by: hijkzzz <janhu9527@gmail.com>
 2025-04-24 15:13:04 +08:00
dependabot[bot] 738b086cfd
Bump nokogiri from 1.18.4 to 1.18.8 (#55) 
Bumps [nokogiri](https://github.com/sparklemotion/nokogiri) from 1.18.4 to 1.18.8.
- [Release notes](https://github.com/sparklemotion/nokogiri/releases)
- [Changelog](https://github.com/sparklemotion/nokogiri/blob/main/CHANGELOG.md)
- [Commits](https://github.com/sparklemotion/nokogiri/compare/v1.18.4...v1.18.8)

---
updated-dependencies:
- dependency-name: nokogiri
  dependency-version: 1.18.8
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-04-23 20:05:23 +01:00
Aritra Roy Gosthipaty dcfdf596c1
[Add] Blog post on transformers backend integration with vLLM (#50) 
* add transformers backend blog post

Signed-off-by: ariG23498 <aritra.born2fly@gmail.com>

OK

Signed-off-by: ariG23498 <aritra.born2fly@gmail.com>

* Apply suggestions from code review

Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: ariG23498 <aritra.born2fly@gmail.com>

* Update _posts/2025-04-11-transformers-backend.md

Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: ariG23498 <aritra.born2fly@gmail.com>

OK

Signed-off-by: ariG23498 <aritra.born2fly@gmail.com>

* Update _posts/2025-04-11-transformers-backend.md

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

---------

Signed-off-by: ariG23498 <aritra.born2fly@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-16 12:31:00 +01:00
Harry Mellor 5e19ec38f9
Add support for GFM admonitions in the blog (#52) 
* Add support for GFM admonitions in the blog

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

* Update `jekyll-gfm-admonitions`

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

---------

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-16 11:42:30 +01:00
Lucia Fang 447290f5c1
remove tips for attn_temperature_tuning in llama4 blog (#51) 
Since we auto-enable this with max-model-len > 32 in PR https://github.com/vllm-project/vllm/pull/16439, this tip can be removed to avoid confusion.
 2025-04-15 11:17:59 -07:00
Lucia Fang e4a43dab00
remove attn_temperature_tuning in default user guide (#49) 
Signed-off-by: Lu Fang <fanglu@fb.com>
 2025-04-08 12:03:41 +01:00
Lucia Fang 3eb4d4d737
Update llama4 documentation to use the right settings for long context (#48) 2025-04-07 13:08:47 -07:00
Simon Mo de34b1ce54
llama4 post (#47) 
* llama4 post

Signed-off-by: simon-mo <simon.mo@hey.com>

* 8 images

Signed-off-by: simon-mo <simon.mo@hey.com>

* comments

Signed-off-by: simon-mo <simon.mo@hey.com>

* charlotte edits

Signed-off-by: simon-mo <simon.mo@hey.com>

* remove dup paragraphs

Signed-off-by: Roger Wang <ywang@roblox.com>

* add multimodal

Signed-off-by: Roger Wang <ywang@roblox.com>

* update model id

Signed-off-by: Roger Wang <ywang@roblox.com>

* point to 0.8.3 branch

Signed-off-by: Roger Wang <ywang@roblox.com>

---------

Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
 2025-04-05 23:44:57 -07:00
dependabot[bot] 79dc7969a9
Bump nokogiri from 1.18.3 to 1.18.4 (#46) 
Bumps [nokogiri](https://github.com/sparklemotion/nokogiri) from 1.18.3 to 1.18.4.
- [Release notes](https://github.com/sparklemotion/nokogiri/releases)
- [Changelog](https://github.com/sparklemotion/nokogiri/blob/main/CHANGELOG.md)
- [Commits](https://github.com/sparklemotion/nokogiri/compare/v1.18.3...v1.18.4)

---
updated-dependencies:
- dependency-name: nokogiri
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-03-22 17:33:10 +00:00
TJian f5100370f3
add ptpc-fp8 amd blogpost (#45) 
Signed-off-by: tanpinsiang <pinsiang.tan@embeddedllm.com>
Co-authored-by: tanpinsiang <pinsiang.tan@embeddedllm.com>
 2025-03-20 17:22:42 +00:00
dependabot[bot] ded60c9338
Bump json from 2.10.1 to 2.10.2 (#44) 
Bumps [json](https://github.com/ruby/json) from 2.10.1 to 2.10.2.
- [Release notes](https://github.com/ruby/json/releases)
- [Changelog](https://github.com/ruby/json/blob/master/CHANGES.md)
- [Commits](https://github.com/ruby/json/compare/v2.10.1...v2.10.2)

---
updated-dependencies:
- dependency-name: json
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-03-17 16:50:33 +00:00
Harry Mellor 0f46e1904f
Add `MathJax` support (#43) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-03-17 16:20:03 +00:00
Harry Mellor 4d264ee9a0
Update installation doc URLs (#40) 
Follow up to https://github.com/vllm-project/vllm/pull/14556.

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-03-10 10:43:02 -07:00
Harry Mellor 7e828ff7a5
Bump `uri` gem version to resolve vulnerability (#39) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-03-04 13:05:59 +01:00
Harry Mellor 3128f43921
Fix vulnerabilities and improve CI (#37) 
* Run build in PR CI

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

* Update Gemfile.lock to remove vulnerable package

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

---------

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-25 14:09:57 +00:00
Jiaxin Shan 57e3d78db2
Update figure size for aibrix release blog (#36) 
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
 2025-02-21 14:31:58 -08:00
Jiaxin Shan 2c056850c0
Add aibrix release blog post (#35) 
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
 2025-02-21 14:02:48 -08:00
Harry Mellor cff357d242
Add logo for `jekyll-seo-tag` (#34) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-21 17:32:06 +00:00
Harry Mellor 4561c61199
Add auto darkmode (#33) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-21 16:18:35 +00:00
Harry Mellor 9b5ad206c3
Use remote theme instead of including it locally (#32) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-21 15:56:04 +00:00
Harry Mellor f0a320256b
Add social links (#31) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-21 13:30:10 +00:00
Guspan Tanadi 2ae1f8efa2
docs(2025-01-21-stack-release): related repo links (#30) 2025-02-21 11:19:17 +00:00
Murali Andoorveedu a2efb9d767
Add distributed inference blog post (#27) 
* Add distributed inference blog post

Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>

* Update _posts/2025-02-17-distributed-inference.md

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

---------

Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-19 17:29:26 +00:00
Harry Mellor 278a6a482b
Remove unused `release-drafter` files (#28) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-19 17:13:33 +00:00
Guspan Tanadi d9c2a8e934
Fix links format Installation (#26) 
* Fix links format Installation

* Update _posts/2024-09-05-perf-update.md

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

---------

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-18 10:04:23 +00:00
Harry Mellor f74517c7fe
Update README.md (#25) 2025-02-07 00:44:22 +00:00
Harry Mellor 95bece8af7
Update jekyll.yml 2025-02-07 00:23:31 +00:00
Simon Mo dc8145c2ef
Update jekyll.yml 2025-02-06 16:13:58 -08:00
Harry Mellor 0871fab202
Create CNAME 2025-02-07 00:12:24 +00:00
Yuan Tang 3d55f5c5cf
Mention the need to request access to Llama models in 2025-01-27-intro-to-llama-stack-with-vllm.md (#23) 2025-02-06 23:54:40 +00:00
Harry Mellor 55403d351c
Merge pull request #24 from vllm-project/pages-deploy 
Fix `jekyll.yml` build
 2025-02-06 23:44:27 +00:00
Harry Mellor ab75e750f3 Update to latest ruby and add x86 platform to lock 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-06 23:41:24 +00:00
Harry Mellor f069f39046
Add CI platform to jekyll.yml 2025-02-06 23:23:12 +00:00
Harry Mellor 7d1357654e
Add `ruby-version` back 2025-02-06 23:18:43 +00:00
Harry Mellor 8b073f6ed4
Update ruby/setup-ruby in jekyll.yml 2025-02-06 23:13:29 +00:00
Harry Mellor ba7167dc85
Create jekyll.yml 2025-02-06 23:04:16 +00:00
Michael Goin 549b72b221
Merge pull request #22 from hmellor/patch-1 2025-01-30 10:18:56 -05:00
Harry Mellor ff274c498a
Fix documentation link in V1 blog 2025-01-30 15:05:30 +00:00
Simon Mo 8f3b817f7b
Merge pull request #21 from terrytangyuan/patch-2 
Correct inference provider config for K8s deployment 2025-01-27-intro-to-llama-stack-with-vllm.md
 2025-01-29 09:47:50 -08:00
Simon Mo c8a5fd3533
Merge pull request #20 from terrytangyuan/patch-1 
Bump copyright year to 2025 in _config.yml
 2025-01-29 09:47:24 -08:00
Yuan Tang 288580d57f
Update 2025-01-27-intro-to-llama-stack-with-vllm.md 2025-01-29 12:19:18 -05:00
Yuan Tang cfd9e3faf4
Correct inference provider config for K8s deployment 2025-01-27-intro-to-llama-stack-with-vllm.md 2025-01-29 12:01:21 -05:00
Yuan Tang 8fcaa7ee63
Bump copyright year to 2025 in _config.yml 2025-01-27 23:25:29 -05:00
Simon Mo 01664a2767
Merge pull request #19 from terrytangyuan/patch-1 
Update 2025-01-27-intro-to-llama-stack-with-vllm.md
 2025-01-27 11:53:27 -08:00
Yuan Tang 1146ced6d0
Update 2025-01-27-intro-to-llama-stack-with-vllm.md 2025-01-27 14:49:59 -05:00
Simon Mo d28e88240d
Merge pull request #15 from Hanchenli/main 
Adding production-stack post
 2025-01-27 11:37:38 -08:00
Simon Mo c56753c0df
Merge pull request #18 from hmellor/fix-dead-links 
Fix dead links to installation docs
 2025-01-27 11:37:23 -08:00
Simon Mo 03662292d6
Merge pull request #16 from terrytangyuan/llama-stack 
New blog: Introducing vLLM Inference Provider in Llama Stack
 2025-01-27 11:37:16 -08:00
WoosukKwon 41638ef1c5 Add thumbnail to V1 blog post 
Signed-off-by: WoosukKwon <woosuk.kwon@berkeley.edu>
 2025-01-27 08:15:55 -08:00