Commits · a3bc76e4b565fd14f13710c696fe47787b008f1f · OpenDAS / vllm_cscc · GitLab

23 Jun, 2025 16 commits
- [CI/Build] Push latest tag for cpu and neuron docker image (#19897) · a3bc76e4
  22quinn authored Jun 23, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  a3bc76e4
- [Feature] Support sequence parallelism for static fp8 quantization (#19181) · e6327c9b
  cascade authored Jun 23, 2025
```
Signed-off-by: cascade812 <cascade812@outlook.com>
```
  e6327c9b
- [Misc] Add type alias `ReqId` and `EngineId` for better readability (#19880) · d0132f02
  lkchen authored Jun 23, 2025
```
Signed-off-by: Linkun Chen <github@lkchen.net>
```
  d0132f02
- [Bugfix][v1] Fix step pooler implementation and step pooling usage in v1 (#19956) · 61f4fc5d
  Isotr0py authored Jun 24, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  61f4fc5d
- [EP+DP] Optimize the little operations in the DeepGEMM + DeepEP low latency case (#19885) · 68aaeb37
  Tyler Michael Smith authored Jun 23, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  68aaeb37
- [Docs] Fix syntax highlighting of shell commands (#19870) · c3649e4f
  Lukas Geiger authored Jun 23, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  c3649e4f
- [doc] improve readability for long commands (#19920) · 53243e5c
  Reid authored Jun 23, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  53243e5c
- [Bugfix] Fix CI bitsandbytes failure (#19969) · a6e6604d
  Jee Jee Li authored Jun 23, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a6e6604d
- [doc] use MkDocs collapsible blocks - supplement (#19973) · b82e0f82
  Reid authored Jun 23, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  b82e0f82
- [Doc] Update V1 status for decoder-only embedding models (#19952) · 5111642a
  Isotr0py authored Jun 23, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  5111642a
- [BugFix][P/D] Fix for cases where _recving_transfers can be cleaned up when... · 1bcd15ed
  lkchen authored Jun 22, 2025
```
[BugFix][P/D] Fix for cases where _recving_transfers can be cleaned up when *all* transfer done (#19874)
Signed-off-by: Linkun Chen <github@lkchen.net>
```
  1bcd15ed
- [P/D][NixlConnector] Support `tp_size > num_kv_heads` deployments (#19691) · 2ebff5b7
  Nicolò Lucchesi authored Jun 23, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  2ebff5b7
- [doc] Fold long code blocks to improve readability (#19926) · f17aec0d
  Reid authored Jun 23, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  f17aec0d
- Fix(models/siglip): Add compatibility for Gemma models quantized by llm-compressor (#19643) · 493c2753
  Vensen authored Jun 23, 2025
```
Signed-off-by: Vensenmu <vensenmu@gmail.com>
```
  493c2753
- [Misc] Configurable timeout for execute_model RPC calls via env var (#19544) · f39ab2d4
  jinqinn authored Jun 23, 2025
```
Signed-off-by: jinqinn <goodqinjin@163.com>
```
  f39ab2d4
- [Core] feat: Implement Priority Scheduling in V1 Engine (#19057) · 4a0f7888
  amit authored Jun 23, 2025
```
Signed-off-by: amit <amit.man@gmail.com>
Co-authored-by: Roger Wang <Rogerw0108@gmail.com>
```
  4a0f7888
22 Jun, 2025 10 commits
- [Perf][CLI] Improve overall startup time (#19941) · c4cf2606
  Aaron Pham authored Jun 22, 2025
  
  c4cf2606
- [BugFix] Add an env to disable moe chunking to work around compile incompatibility (#19642) · 33d51f59
  Ye (Charlotte) Qi authored Jun 22, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  33d51f59
- [Chore] dedup logs (#19955) · e91386cd
  Aaron Pham authored Jun 22, 2025
  
  e91386cd
- [Misc] Simplify vllm bench cli subcommand implementation (#19948) · 2c11a29f
  Ye (Charlotte) Qi authored Jun 22, 2025
  
  2c11a29f
- [Misc] Update model-specific PR tagging (#19949) · c76a506b
  Roger Wang authored Jun 22, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.me>
```
  c76a506b
- [doc] use snippets for contact us (#19944) · ec0db6f5
  Reid authored Jun 22, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  ec0db6f5
- [CI/Build] Auto tag perf benchmarks related PRs (#19943) · c305a210
  22quinn authored Jun 22, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  c305a210
- [Benchmark] fix request loss if "ping" is returned (#19535) · 202c5df9
  Wang, Yi authored Jun 22, 2025
```
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  202c5df9
- [MISC] add cpu_kvcache_space_bytes to CacheConfig (#19812) · 2bb246b8
  Ning Xie authored Jun 22, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  2bb246b8
- [Misc] add vllm_config in __init__ (#19866) · 4c409cab
  Ning Xie authored Jun 22, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  4c409cab
21 Jun, 2025 5 commits
- [Docs] Add GPT2ForSequenceClassification to supported models in docs (#19932) · 3b1e4c6a
  Adrian authored Jun 21, 2025
```
Signed-off-by: nie3e <adrcwiek@gmail.com>
```
  3b1e4c6a
- [Multimodal] Optimize Qwen2/2.5-VL startup time (#19756) · 2c5302fa
  Woosuk Kwon authored Jun 21, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.me>
```
  2c5302fa
- [doc] add contact us in community (#19922) · caa680fd
  Reid authored Jun 22, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  caa680fd
- [New model support]Support Tarsier2 (#19887) · c3bf9bad
  汪志鹏 authored Jun 21, 2025
```
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
```
  c3bf9bad
- [Bugfix] Fix bnb 8bit model weights loading (#19917) · 6f170f11
  Isotr0py authored Jun 21, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  6f170f11
20 Jun, 2025 9 commits
- Fix: Check the type of params to be a Sequence not list. (#19910) · 8ca81bb0
  Rabin Adhikari authored Jun 21, 2025
```
Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com>
```
  8ca81bb0
- [Misc] Clean up useless code (#19889) · e773a9e1
  wangxiyuan authored Jun 21, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  e773a9e1
- [Kernel] mark TorchSDPABackend swap_blocks NotImplementedError (#19749) · 71baf85a
  Ning Xie authored Jun 21, 2025
  
  71baf85a
- [CPU][CI] Fallback sliding window to v0 and fix CPU pooling model tests (#19901) · 79f2f1c2
  Li, Jiang authored Jun 20, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  79f2f1c2
- Export NaNs in logits to scheduler_stats if output is corrupted (#18777) · 2e3e3c86
  Vlad Tiberiu Mihailescu authored Jun 20, 2025
```
Signed-off-by: Vlad Mihailescu <vtmihailescu@gmail.com>
```
  2e3e3c86
- [custom_op][vllm-plugin] update custom_op class to use op_registry (#19164) · 7e8977fc
  Chendi.Xue authored Jun 20, 2025
```
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
```
  7e8977fc
- [Model] GPT2ForSequenceClassification model (#19663) · f1e840e8
  Adrian authored Jun 20, 2025
```
Signed-off-by: nie3e <adrcwiek@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  f1e840e8
- [Fix] import regex instead of re (#19875) · 7771d1de
  Thomas Parnell authored Jun 20, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  7771d1de
- [Kernel] correct cpu worker function parameter type (#19745) · 71d12195
  Ning Xie authored Jun 20, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  71d12195