Commits · a55c95096b3537edfbbb7a5eafae0b0475c5ef07 · OpenDAS / vllm_cscc · GitLab

26 Jul, 2025 10 commits
- Correctly kill vLLM processes after finishing serving benchmarks (#21641) · a55c9509
  Huy Do authored Jul 25, 2025
```
Signed-off-by: Huy Do <huydhn@gmail.com>
```
  a55c9509
- [Docs] add offline serving multi-modal video input expamle Qwen2.5-VL (#21530) · 97349fe2
  WeiQing Chen authored Jul 26, 2025
```
Signed-off-by: David Chen <530634352@qq.com>
```
  97349fe2
- [Model] Ultravox: Support Llama 4 and Gemma 3 backends (#17818) · 62965de5
  Farzad Abdolhosseini authored Jul 26, 2025
```
Signed-off-by: Farzad Abdolhosseini <farzad@fixie.ai>
Signed-off-by: Patrick Li <patrick8289@gmail.com>
Co-authored-by: Patrick Li <patrick8289@gmail.com>
```
  62965de5
- [Feature] Add support for MoE models in the calibration-free RTN-based quantization (#20766) · 7ae75fa6
  Alex Kogan authored Jul 25, 2025
```
Signed-off-by: Alex Kogan <alex.kogan@oracle.com>
```
  7ae75fa6
- [TPU] Update ptxla nightly version to 20250724 (#21555) · f1b286b2
  Chengji Yao authored Jul 25, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  f1b286b2
- [Bugfix] Always set RAY_ADDRESS for Ray actor before spawn (#21540) · c7742d61
  Rui Qiao authored Jul 25, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  c7742d61
- [Bugfix] Fix sync_and_slice_intermediate_tensors (#21537) · cea96a01
  Rui Qiao authored Jul 25, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  cea96a01
- Add interleaved RoPE test for Llama4 (Maverick) (#21478) · 2eddd437
  Yong Hoon Shin authored Jul 25, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  2eddd437
- [Perf] Cuda Kernel for Int8 Per Token Group Quant (#21476) · 75d29cf4
  Wentao Ye authored Jul 25, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  75d29cf4
- Add Unsloth to RLHF.md (#21636) · 41d3082c
  Daniel Han authored Jul 25, 2025
  
  41d3082c
25 Jul, 2025 30 commits
- [TPU][Test] Rollback PR-21550. (#21619) · 7cfea0df
  QiliangCui authored Jul 25, 2025
```
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
```
  7cfea0df
- [Docs] add auto-round quantization readme (#21600) · 5ac3168e
  Wenhua Cheng authored Jul 25, 2025
```
Signed-off-by: Wenhua Cheng <wenhua.cheng@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  5ac3168e
- [CI] Unifying Dockerfiles for ARM and X86 Builds (#21343) · 396ee941
  Kebe authored Jul 25, 2025
```
Signed-off-by: Kebe <mail@kebe7jun.com>
```
  396ee941
- Add support for Prithvi in Online serving mode (#21518) · e189b50f
  mgazz authored Jul 25, 2025
```
Signed-off-by: Michele Gazzetti <michele.gazzetti1@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  e189b50f
- [Kernel] Improve machete memory bound perf (#21556) · 136d750f
  czhu-cohere authored Jul 25, 2025
```
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
```
  136d750f
- [ROCm][AITER] Enable fp8 kv cache on rocm aiter backend. (#20295) · b3caeb82
  who who who authored Jul 25, 2025
```
Signed-off-by: fsx950223 <fsx950223@outlook.com>
Signed-off-by: amd-ruitang3 <Rui.Tang2@amd.com>
Co-authored-by: amd-ruitang3 <Rui.Tang2@amd.com>
```
  b3caeb82
- [Model] Replace Mamba2 RMSNorm Gated with Fused Triton Kernel (#20839) · eab2f398
  Chih-Chieh Yang authored Jul 25, 2025
```
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
Signed-off-by: Yu Chin Fabian Lim <fabian.lim@gmail.com>
Signed-off-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com>
Co-authored-by: Yu Chin Fabian Lim <fabian.lim@gmail.com>
```
  eab2f398
- [Frontend] Add request_id to the Request object so they can be controlled... · 9fe98d42
  kourosh hakhamaneshi authored Jul 25, 2025
```
[Frontend] Add request_id to the Request object so they can be controlled better via external load balancers (#21009)
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
```
  9fe98d42
- [MODEL] New model support for naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B (#20931) · 29c6fbe5
  bigshanedogg authored Jul 25, 2025
```
Signed-off-by: bigshanedogg <bigshane319@gmail.com>
```
  29c6fbe5
- [Model] Fix Ernie4.5MoE e_score_correction_bias parameter (#21586) · c72f049c
  xyxinyang authored Jul 25, 2025
```
Signed-off-by: zhouchong <zhouchong03@baidu.com>
Co-authored-by: zhouchong <zhouchong03@baidu.com>
```
  c72f049c
- [Bugfix][Logprobs] Fix logprobs op to support more backend (#21591) · f3a683b7
  Mengqing Cao authored Jul 25, 2025
```
Signed-off-by: MengqingCao <cmq0113@163.com>
```
  f3a683b7
- [V1] Get supported tasks from model runner instead of model config (#21585) · 46d81d69
  Cyrus Leung authored Jul 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  46d81d69
- [Quantization] Enable BNB support for more MoE models (#21370) · 5c3f2628
  Jee Jee Li authored Jul 25, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  5c3f2628
- [Bugfix] GGUF: fix AttributeError: 'PosixPath' object has no attribute 'startswith' (#21579) · 7311f744
  Kebe authored Jul 25, 2025
```
Signed-off-by: Kebe <mail@kebe7jun.com>
```
  7311f744
- Add H20-3e fused MoE kernel tuning configs for Qwen3-Coder-480B-A35B-Instruct (#21598) · 8ed01e32
  Xu Wenqing authored Jul 25, 2025
```
Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
```
  8ed01e32
- [Tests] Harden DP tests (#21508) · e38e96a3
  Nick Hill authored Jul 25, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  e38e96a3
- [TPU][Bugfix] fix OOM issue in CI test (#21550) · 40d86ee4
  Chengji Yao authored Jul 24, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  40d86ee4
- [Misc] Removed undefined cmake variables MOE_PERMUTE_ARCHS (#21262) · 85d051f0
  Yang Chen authored Jul 24, 2025
```
Signed-off-by: Yang Chen <yangche@fb.com>
```
  85d051f0
- [CI/Build] fix cpu_extension for apple silicon (#21195) · 5140f54b
  Ignacio Sica authored Jul 25, 2025
```
Signed-off-by: ignaciosica <mignacio.sica@gmail.com>
```
  5140f54b
- [Misc][Tools] make max-model-len a parameter in auto_tune script (#21321) · 947edd09
  Chengji Yao authored Jul 24, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  947edd09
- [Model] Fix a check for None but the return value was empty list in Gemma3 MM... · fde60ee7
  hfan authored Jul 25, 2025
```
[Model] Fix a check for None but the return value was empty list in Gemma3 MM vision_embeddings (#21479)
Signed-off-by: Hongmin Fan <fanhongmin@google.com>
```
  fde60ee7
- [Model] Support tensor parallel for timm ViT in Deepseek_vl2 (#21494) · b38bc652
  Jason Gu authored Jul 25, 2025
```
Signed-off-by: wzqd <1057337859@qq.com>
```
  b38bc652
- [Bugfix] fix modelscope snapshot_download serialization (#21536) · adaf2c6d
  Ning Xie authored Jul 25, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  adaf2c6d
- [CI] Update CODEOWNERS for CPU and Intel GPU (#21582) · 42343f1f
  Li, Jiang authored Jul 25, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  42343f1f
- Integrate TensorSchema with shape validation for Phi3VImagePixelInputs (#21232) · 965bc71b
  Benji Beck authored Jul 24, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  965bc71b
- [Docs] Add `requirements/common.txt` to run unit tests (#21572) · 807a328b
  Zhou Fang authored Jul 24, 2025
```
Signed-off-by: Zhou Fang <fang.github@gmail.com>
```
  807a328b
- [TPU][Test] Temporarily suspend this MoE model in test_basic.py. (#21560) · e0be2c4d
  QiliangCui authored Jul 24, 2025
```
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
```
  e0be2c4d
- [DP] Support api-server-count > 0 in hybrid DP LB mode (#21510) · 9c8b2c2a
  Nick Hill authored Jul 25, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  9c8b2c2a
- [Bugfix] DeepGemm utils : Fix hardcoded type-cast (#21517) · 2212cd6c
  Varun Sundar Rabindranath authored Jul 25, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  2212cd6c
- [Kernel] adding fused_moe configs for upcoming granite4 (#21332) · ce3a9b13
  Burkhard Ringlein authored Jul 25, 2025
```
Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  ce3a9b13