Commits · 467bef18a353e8ca133a0a5611d6f4384ea351b6 · OpenDAS / vllm_cscc · GitLab

10 Jun, 2025 14 commits
- [BugFix][FlashInfer] Fix attention backend interface mismatch with unexpected... · 467bef18
  Rachel Guo authored Jun 10, 2025
```
[BugFix][FlashInfer] Fix attention backend interface mismatch with unexpected keyword `use_irope` (#19134)
Signed-off-by: Yunqiu Guo <guorachel@meta.com>
```
  467bef18
- Revert "[v1] Add fp32 support to v1 engine through flex attn" (#19404) · 5f1ac1e1
  Isotr0py authored Jun 10, 2025
  
  5f1ac1e1
- Automatically bind CPU OMP Threads of a rank to CPU ids of a NUMA node. (#17930) · 9368cc90
  Louie Tsai authored Jun 09, 2025
```
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Co-authored-by: Li, Jiang <bigpyj64@gmail.com>
```
  9368cc90
- Add clear documentation around the impact of debugging flag (#19369) · 32b3946b
  Anna Pendleton authored Jun 09, 2025
```
Signed-off-by: Anna Pendleton <pendleton@google.com>
```
  32b3946b
- [Misc] refactor neuron_multimodal and profiling (#19397) · 6b1391ca
  Reid authored Jun 10, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  6b1391ca
- Add security warning to bug report template (#19365) · a3f66e75
  Russell Bryant authored Jun 10, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
```
  a3f66e75
- [Core] Batch multi modal input using pinned memory (#19169) · 319cb1e3
  Lukas Geiger authored Jun 10, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  319cb1e3
- [Bugfix] Fix modelscope token passed in (#19389) · 1efef716
  Li Wang authored Jun 10, 2025
```
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  1efef716
- [Core] Use tuple for kv cache group block ids (#19175) · 646d62f6
  Nick Hill authored Jun 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  646d62f6
- [Frontend] Add tqdm_leave_pbar to control progress bar visibility (#19357) · 6cd4ae8a
  Reid authored Jun 10, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  6cd4ae8a
- Fix docs/mkdocs/hooks/remove_announcement.py (#19382) · c016047e
  Harry Mellor authored Jun 10, 2025
  
  c016047e
- Use xla flag to improve the quantized model performance (#19303) · 9af6d22e
  XiongfeiWei authored Jun 09, 2025
```
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
```
  9af6d22e
- [Bugfix] Fix benchmark_moe.py (#19016) · 4589b940
  Tianyu Guo authored Jun 10, 2025
```
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
```
  4589b940
- [V1] Reuse V0's memory_profiling util for gpu worker memory profiling (#19312) · cc867be1
  Ye (Charlotte) Qi authored Jun 09, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  cc867be1
09 Jun, 2025 19 commits
- [Misc] Fix a config typo in disable_hybrid_kv_cache_manager configuration (#19383) · 3a7cd627
  Siyuan Liu authored Jun 09, 2025
```
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
```
  3a7cd627
- [HOT-FIX] Add `kv_sharing_target_layer_name` argument to cutlass_mla backend (#19374) · 8058c911
  Pavani Majety authored Jun 09, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  8058c911
- [TPU]Fix KV cache sharing tests (#19371) · 7d44c469
  Siyuan Liu authored Jun 09, 2025
  
  7d44c469
- [Frontend] Make TIMEOUT_KEEP_ALIVE configurable through env var (#18472) · 31f58be9
  liusiqian-tal authored Jun 10, 2025
```
Signed-off-by: liusiqian <liusiqian@tal.com>
```
  31f58be9
- [Quantization] Bump compressed-tensors version (#19295) · ebb2f383
  Kyle Sayers authored Jun 09, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  ebb2f383
- [Bugfix][Core] Prevent token lengths exceeding `max_model_len` in V0 (#19348) · c1c7dbbe
  22quinn authored Jun 09, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  c1c7dbbe
- [Misc] Fixes and Optimizations for DeepEP + DeepGEMM combination. (#19298) · 5cf2daea
  Varun Sundar Rabindranath authored Jun 09, 2025
```
Signed-off-by: Varun <vsundarr@redhat.com>
Co-authored-by: Varun <vsundarr@redhat.com>
```
  5cf2daea
- [v1] Add fp32 support to v1 engine through flex attn (#19319) · b8089195
  Isotr0py authored Jun 09, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  b8089195
- [full_graph] Fix query_start_loc padding (#19321) · 770e5dcd
  Yinghai Lu authored Jun 09, 2025
```
Signed-off-by: Yinghai Lu <yinghai@thinkingmachines.ai>
```
  770e5dcd
- [Docs] Fix a bullet list in usage/security.md (#19358) · c57c9415
  Michael Yao authored Jun 09, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  c57c9415
- [CI] Introduce rules for llama auto-label (#19323) · 01810f92
  Lu Fang authored Jun 09, 2025
```
Signed-off-by: Lu Fang <lufang@fb.com>
```
  01810f92
- [Fix] Allow kernel compilation for CUDA capability 8.7 (#19328) · 59abbd84
  Conroy Cheers authored Jun 09, 2025
```
Signed-off-by: Conroy Cheers <conroy@corncheese.org>
```
  59abbd84
- [CI/Build] Fix LoRA test (#19350) · 95a6568b
  Jee Jee Li authored Jun 09, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  95a6568b
- [Doc] Fix description in the Automatic Prefix Caching design doc (#19333) · 0eca5eac
  Se7en authored Jun 09, 2025
```
Signed-off-by: cr7258 <chengzw258@163.com>
```
  0eca5eac
- [doc] improve ci doc (#19307) · 12e58292
  Reid authored Jun 09, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  12e58292
- [Misc] Cleanup compilation tests (#19343) · 3a4d4177
  Richard Zou authored Jun 09, 2025
```
Signed-off-by: rzou <zou3519@gmail.com>
```
  3a4d4177
- [Frontend] Remove unreachable code from llm.py (#19288) · 8335667c
  Kseniya Parkhamchuk authored Jun 08, 2025
```
Signed-off-by: KsuParkhamchuk <k.parkhamchuk@gmail.com>
```
  8335667c
- [Misc] Add documentation update reminder to PR template (#19289) · e1c4380d
  Isotr0py authored Jun 09, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  e1c4380d
- [Deprecation] Remove `inputs` arg fallback in Engine classes (#18799) · e31ae3de
  Cyrus Leung authored Jun 09, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  e31ae3de
08 Jun, 2025 7 commits
- [Bugfix] model_max_length should consider max_model_len in tokenizer_config (#19201) · 2ffb9b6e
  wang.yuqi authored Jun 08, 2025
  
  2ffb9b6e
- [Multi Modal] Add an env var for message queue max chunk bytes (#19242) · cda10fa3
  jennyyyyzhen authored Jun 08, 2025
```
Signed-off-by: yZhen <yZhen@fb.com>
Co-authored-by: yZhen <yZhen@fb.com>
```
  cda10fa3
- [Quantization] Add compressed-tensors NVFP4 support (#18312) · c123bc33
  Dipika Sikka authored Jun 08, 2025
  
  c123bc33
- [Hardware][POWER] Add IBM POWER11 Support to CPU Extension Detection (#19082) · b9a1791e
  Akash kaothalkar authored Jun 08, 2025
```
Signed-off-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
```
  b9a1791e
- Add H20-3e fused MoE kernel tuning configs for Qwen3-235B-A22B (#19315) · 989dcee9
  Xu Wenqing authored Jun 08, 2025
```
Signed-off-by: Xu Wenqing <xuwq1993@qq.com>
```
  989dcee9
- [Misc] Change tests/compile to use VLLM_V1 by default (#19302) · 3d64d366
  Richard Zou authored Jun 08, 2025
```
Signed-off-by: rzou <zou3519@gmail.com>
```
  3d64d366
- [Bugfix] Re-enable use_cudagraph in vLLM v1 (#19299) · eaa2e510
  Richard Zou authored Jun 07, 2025
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  eaa2e510