Commits · 77f62613f9eb0963dffca1f58d22f718505e80c7 · OpenDAS / vllm_cscc · GitLab

10 Sep, 2025 18 commits
- Consolidate rendering parameters into RenderConfig dataclass (#24543) · 77f62613
  Flora Feng authored Sep 10, 2025
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  77f62613
- [Bugfix] Guard `_may_reorder_batch` for encoder-only models on CPU (#24319) (#24348) · feaf202e
  Remy authored Sep 10, 2025
```
Signed-off-by: Remy <eunhwan.shin@dtonic.io>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
```
  feaf202e
- [docs] promo pytorch conf and ray summit (#24562) · 91130ae3
  Simon Mo authored Sep 09, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  91130ae3
- [Docs] Enable relative links in examples to function when rendered in the docs (#24041) · e4082728
  Harry Mellor authored Sep 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e4082728
- [Bugfix] Update Run:AI Model Streamer Loading Integration (#23845) · 4377b1ae
  pwschuurman authored Sep 09, 2025
```
Signed-off-by: Omer Dayan (SW-GPU) <omer@run.ai>
Signed-off-by: Peter Schuurman <psch@google.com>
Co-authored-by: Omer Dayan (SW-GPU) <omer@run.ai>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  4377b1ae
- [Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271) · 009d689b
  Chenheli Hua authored Sep 09, 2025
```
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
```
  009d689b
- [gpt-oss] Cache permute indices for faster MXFP4 MoE layer loading (#24154) · 0efdb5c3
  Wei authored Sep 09, 2025
```
Signed-off-by: Wei Wei <wwei6@meta.com>
```
  0efdb5c3
- [BugFix][Spec Decode] Fix out-of-range index triggered by eagle3; re-enable... · 53b42f41
  Wenlong Wang authored Sep 09, 2025
```
[BugFix][Spec Decode] Fix out-of-range index triggered by eagle3; re-enable test for LlamaForCausalLMEagle3 (#24392)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
```
  53b42f41
- [P/D] MultiConnector supports shutdown (#24425) · 309d7aa4
  Chauncey authored Sep 10, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  309d7aa4
- [KV Connector] More async support for `get_num_new_matched_tokens` (#23620) · b4a01aaf
  Yihua Cheng authored Sep 09, 2025
```
Signed-off-by: ApostaC <yihua98@uchicago.edu>
```
  b4a01aaf
- [CI] Adjust threshold for flaky ngram spec decoding test (#24528) · 83dd28aa
  Nick Hill authored Sep 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  83dd28aa
- [BugFix] Fix async core engine client finalizer (#24540) · f88e8401
  Nick Hill authored Sep 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  f88e8401
- [Hardware][Apple-CPU] Enable native bfloat16 on Apple Silicon (M2 and later) (#24129) · 3c2156b3
  Ignacio Sica authored Sep 10, 2025
```
Signed-off-by: ignaciosica <mignacio.sica@gmail.com>
```
  3c2156b3
- [CI] Retry flaky fp8 cutlass mla tests (#24536) · 7e7db043
  Nick Hill authored Sep 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  7e7db043
- Add @heheda12345 to CODEOWNERS of KVCacheManager related code (#24546) · 41f160b9
  Chen Zhang authored Sep 09, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  41f160b9
- [Perf] Convert np array to torch tensor to index into block table for attn chunking (#24474) · dc625ea6
  Yong Hoon Shin authored Sep 09, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  dc625ea6
- [Bugfix] Fix for 24530. Fix naive all2all shared expert overlap. (#24538) · b23fb786
  bnellnm authored Sep 09, 2025
  
  b23fb786
- [Bugfix] Improve EPLB config validation error message (#24524) · 561f38dc
  Tyler Michael Smith authored Sep 09, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  561f38dc
09 Sep, 2025 22 commits
- [ROCm][Feature] Enable Pipeline Parallelism with Ray Compiled Graph on ROCm (#24275) · 73e688cb
  Charlie Fu authored Sep 09, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  73e688cb
- [Benchmark] Add option to skip oversampling in benchmark (#24457) · fb1a8f93
  Ekagra Ranjan authored Sep 09, 2025
```
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
```
  fb1a8f93
- [Benchmark] Update bench doc with mtbench, blazedit, spec bench (#24450) · 0dc9cbb5
  Ekagra Ranjan authored Sep 09, 2025
```
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
```
  0dc9cbb5
- [Log] Use a relative path in debug-level logs to distinguish files with identical names (#23846) · b5fb3005
  Jiangyun Zhu authored Sep 10, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  b5fb3005
- [Feature] Disallow FlashMLA on Blackwell (#24521) · 15de5ff9
  Wentao Ye authored Sep 09, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  15de5ff9
- [CI] execute all piecewise compilation tests together (#24502) · b8a93076
  Jiangyun Zhu authored Sep 10, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  b8a93076
- [TPU] Fix tpu structured decoding in mixed batches (#24458) · c3f9773b
  Chenyaaang authored Sep 09, 2025
```
Signed-off-by: Chenyaaang <chenyangli@google.com>
```
  c3f9773b
- [Docs] Gemma3n `transcriptions` endpoint support (#24512) · 3707cb25
  Nicolò Lucchesi authored Sep 09, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  3707cb25
- [Misc] bump outlines_core to fix the version conflicts with outlines >= 1.2.0 (#24368) · 920ed46b
  Kazuhiro Serizawa authored Sep 10, 2025
```
Signed-off-by: Kazuhiro Serizawa <nserihiro@gmail.com>
Signed-off-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  920ed46b
- Extend renderer with embedding support and integrate completion endpoint (#24405) · 15cb047e
  Flora Feng authored Sep 09, 2025
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  15cb047e
- [Bugfix] Fix hidden_size for multimodal classification model (#24501) · 9ad0688e
  Jee Jee Li authored Sep 10, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  9ad0688e
- [ROCm][CI/Build] Sync ROCm dockerfiles with the ROCm fork (#24279) · b9a1c4c8
  Gregory Shtrasberg authored Sep 09, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  b9a1c4c8
- [Kernels] Add Flash Linear Attention Kernels (#24518) · 1aa427fd
  youkaichao authored Sep 10, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  1aa427fd
- [Core] Run garbage collector after CUDA graph capture to fix throughput regression (#24128) · 1c63a16b
  Micah Williamson authored Sep 09, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  1c63a16b
- [Bugfix] Handle the edge case in detokenizer where processed tokens contain... · 922d3b40
  d.transposed authored Sep 09, 2025
```
[Bugfix] Handle the edge case in detokenizer where processed tokens contain both `stop` str and `eos` token (#23938)
Signed-off-by: dtransposed <damian.bogunowicz@gmail.com>
```
  922d3b40
- [Model] Systematic support for fp32 head, pooling models part (#23810) · 19332c04
  wang.yuqi authored Sep 09, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  19332c04
- [Compilation][WideEP] Enable Piecewise CUDAGraph for DeepEPHT (#24123) · a55cf41a
  Wentao Ye authored Sep 09, 2025
  
  a55cf41a
- [CI/Build][Doc] Fully deprecate old bench scripts for serving / throughput / latency (#24411) · 6fb27881
  Ye (Charlotte) Qi authored Sep 09, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  6fb27881
- [RL] fast weight update with zmq + ipc handles (#24295) · 3d2a2de8
  Weixiao Huang authored Sep 09, 2025
```
Signed-off-by: huangweixiao <huangweixiao@msh.team>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  3d2a2de8
- [gpt-oss] Validate gpt-oss python tool during initialization (#23856) · 1116590b
  Chen Zhang authored Sep 09, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  1116590b
- [Misc] Add Codex settings to gitignore (#24493) · ccb97338
  Roger Wang authored Sep 09, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.me>
```
  ccb97338
- [Misc] Add claude settings to gitignore (#24492) · 45c9cb58
  Ye (Charlotte) Qi authored Sep 09, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  45c9cb58