Commits · 789562c28c143201a1d2ca35f7adcdf54ef832e5 · OpenDAS / vllm_cscc · GitLab

03 Aug, 2025 5 commits
- Support CUTLASS NVFP4 (w4a4) for Blackwell Geforce GPUs (SM120) (#21309) · 789562c2
  Roberto L. Castro authored Aug 03, 2025
```
Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
```
  789562c2
- [Benchmark] Support ready check timeout in `vllm bench serve` (#21696) · 3f36c325
  Ye (Charlotte) Qi authored Aug 03, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Roger Wang <hey@rogerw.me>
```
  3f36c325
- [Misc] Add tensor schema test coverage for multimodal models (#21754) · 3dddbf1f
  Isotr0py authored Aug 03, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  3dddbf1f
- [Fix] Fix llama4 modelopt weight loading error (#22107) · 337eb23b
  jiahanc authored Aug 03, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  337eb23b
- [Misc] Bump ray to 2.48.0 (#22123) · 2ff46b88
  Rui Qiao authored Aug 02, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  2ff46b88
02 Aug, 2025 21 commits
- Revert "[compile][startup] Disable C++ compilation of symbolic shapes" (#22122) · 554df8a6
  Xiao authored Aug 02, 2025
```
Signed-off-by: Xiao Liu <xiszishu@gmail.com>
```
  554df8a6
- [xpu]support moe models on XPU platform (#21643) · 73e1b9b1
  Yan Ma authored Aug 02, 2025
```
Signed-off-by: yan <yan.ma@intel.com>
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  73e1b9b1
- [V1] [Hybrid] Validate compatibility of attention backend batch reordering at init time (#21557) · 4abfd879
  Thomas Parnell authored Aug 02, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  4abfd879
- [Frontend] Improve error message for too many mm items (#22114) · f5d0f478
  Cyrus Leung authored Aug 02, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  f5d0f478
- [Model] Mamba2 preallocate SSM output tensor to avoid d2d copy overhead (#21075) · b690e348
  Chih-Chieh Yang authored Aug 02, 2025
```
Signed-off-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com>
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
```
  b690e348
- for glm-4.1V update (#22000) · 25373b6c
  Yuxuan Zhang authored Aug 02, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  25373b6c
- [PERF] Use faster way of decode in tokenizer: avoid useless list-to-list conversion (#20000) · 58eee5f2
  Vadim Gimpelson authored Aug 02, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
```
  58eee5f2
- docs: remove deprecated disable-log-requests flag (#22113) · 067c34a1
  Roger Wang authored Aug 02, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.me>
```
  067c34a1
- [Bugfix] Mamba2 remove bugged initial state condition in chunk scan (#22034) · c64861d6
  Chih-Chieh Yang authored Aug 02, 2025
```
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
```
  c64861d6
- Fix test_kv_sharing_fast_prefill flakiness (#22038) · 8564dc94
  Yong Hoon Shin authored Aug 01, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  8564dc94
- [Misc] Getting and passing ray runtime_env to workers (#22040) · 4ac84373
  Rui Qiao authored Aug 01, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  4ac84373
- [FEAT][ROCm] Enable running Flash Attention as ViT attn backend for Qwen-VL... · d3a6f212
  vllmellm authored Aug 02, 2025
```
[FEAT][ROCm] Enable running Flash Attention as ViT attn backend for Qwen-VL models on ROCm platform. (#22069)
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
```
  d3a6f212
- [Attention][DBO] Add support for "splitting" the CommonAttentionMetadata (#21153) · 0edaf752
  Sage Moore authored Aug 01, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  0edaf752
- [Test] Add Unit Test for Batched DeepGEMM (#21559) · 6e8d8c4a
  Wentao Ye authored Aug 01, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  6e8d8c4a
- [BugFix] Improve internal DP load balancing (#21617) · 8d524ce7
  Nick Hill authored Aug 02, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  8d524ce7
- [Speculators][Speculative Decoding] Add Qwen Eagle3 Support (#21835) · 9f9c38c3
  Dipika Sikka authored Aug 01, 2025
```
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
```
  9f9c38c3
- [Misc] DeepGemmExperts : Avoid JIT generation in the hot-path (#21955) · a65f46be
  Varun Sundar Rabindranath authored Aug 02, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  a65f46be
- [Misc] `VLLM_TARGET_DEVICE.lower()` (#22101) · 57393715
  Nicolò Lucchesi authored Aug 02, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  57393715
- [Model] Qwen2.5 VL SiLU-and-Mul (#22066) · ee2eb6ec
  vllmellm authored Aug 02, 2025
```
Signed-off-by: kf <kuanfu.liu@embeddedllm.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: kf <kuanfu.liu@embeddedllm.com>
```
  ee2eb6ec
- [V1][CUDA] Full cudagraph support for FlashInfer (#21367) · 23322431
  fhl2000 authored Aug 02, 2025
  
  23322431
- feat: Add Support GPTQ Quantization MOE on ROCM vllm serve (#21733) · 3654847d
  JartX authored Aug 02, 2025
  
  3654847d
01 Aug, 2025 14 commits
- [Perf] Optimize `reshape_and_cache_flash` CUDA Kernel (#22036) · eefbf4a6
  Wentao Ye authored Aug 01, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  eefbf4a6
- [CI] Initial tests for SM100 Blackwell runner (#21877) · 88faa466
  Michael Goin authored Aug 01, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  88faa466
- [BugFix] Harden distributed DP startup (#21538) · 881e1af4
  Nick Hill authored Aug 01, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  881e1af4
- Add lora test for tp>1 case for TPU. (#21970) · d84b97a3
  XiongfeiWei authored Aug 01, 2025
```
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
```
  d84b97a3
- Introduce RayPPCommunicator for ray-based PP (#21660) · d3317594
  Rui Qiao authored Aug 01, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  d3317594
- [compile][startup] Disable C++ compilation of symbolic shapes (#20836) · 9659bc7f
  Animesh Jain authored Aug 01, 2025
```
Signed-off-by: Animesh Jain <anijain@umich.edu>
```
  9659bc7f
- Fix pre-commit failure for SECURTIY.md (#22102) · 3277e8f9
  Michael Goin authored Aug 01, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  3277e8f9
- [Misc] Minor enhancement of benchmark_moe (#22068) · 8d705996
  Jee Jee Li authored Aug 02, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  8d705996
- Enable headless models for pooling in the Transformers backend (#21767) · 38c8bce8
  Harry Mellor authored Aug 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  38c8bce8
- [Bugfix] [Performance] DeepEPHighThroughput + DeepSeek : Quant before Dispatch (#21837) · ac45c44d
  Varun Sundar Rabindranath authored Aug 01, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  ac45c44d
- security policy: take 1 (#21119) · d6664664
  Huzaifa Sidhpurwala authored Aug 01, 2025
```
Signed-off-by: Huzaifa Sidhpurwala <huzaifas@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
```
  d6664664
- [Bugfix] fix when skip tokenizer init (#21922) · b879ecd6
  rongfu.leng authored Aug 02, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  b879ecd6
- [Bugfix] Fix glm4.1v video inference issue (#22067) · 3f8e9521
  Isotr0py authored Aug 02, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  3f8e9521
- Improve documentation of `ModelConfig.try_get_generation_config` to prevent... · 326a1b00
  Harry Mellor authored Aug 01, 2025
```
Improve documentation of `ModelConfig.try_get_generation_config` to prevent future confusion (#21526)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  326a1b00