Commits · 7812bcf2783acef15b6088ba223f1c94fec42d0d · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "0310029a2fc62171fae87155150326125e082a5a"

05 Sep, 2025 2 commits
- [XPU][P/D] Add XPU support in NixlConnector (#22436) · e599e2c6
  liuzhenwei authored Sep 05, 2025
```
Signed-off-by: zhenwei <zhenwei.liu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  e599e2c6
- [gpt-oss] tool parser supports for /chat/completions [1/n] (#22386) · c29fb540
  Aaron Pham authored Sep 04, 2025
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  c29fb540
04 Sep, 2025 21 commits
- [Frontend] Skip unnecessary detokenization when token_id is requested (#24236) · 65e03893
  Nicolò Lucchesi authored Sep 05, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  65e03893
- [Misc] Have AsyncLLM `custom_stat_loggers` extend default logger list (#20952) · 60b755cb
  Seiji Eicher authored Sep 04, 2025
```
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
Signed-off-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  60b755cb
- QWEN3 Coder Fused MoE kernels Optimization configs (#24266) · 482e52f5
  Saman A. Pour authored Sep 04, 2025
```
Signed-off-by: Saman Keon <samanamp@outlook.com>
```
  482e52f5
- [Misc] Slight improve deepgemm print (#24085) · 94866d7c
  Jee Jee Li authored Sep 05, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  94866d7c
- [Doc]: fix typos in Python comments (#24173) · 83609ca9
  Didier Durand authored Sep 04, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  83609ca9
- [Perf] Freeze core engine proc heap after init (#24008) · e41a0fa3
  Nick Hill authored Sep 04, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  e41a0fa3
- [Misc] Removed force_fp8_e4m3fnuz from FP8LinearOp (#23725) · 37241077
  nvjullin authored Sep 04, 2025
```
Signed-off-by: Julien Lin <jullin@nvidia.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  37241077
- [LoRA]: Add lora support to qwen-2.5-omni (#24231) · c9f7081f
  Yash Pratap Singh authored Sep 04, 2025
  
  c9f7081f
- [XPU] support Triton Attention backend on Intel GPU (#24149) · 16ded21e
  Kunshang Ji authored Sep 04, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  16ded21e
- Use hidden_size_per_head as head_size fallback (#24221) · 2b30afa4
  nopperl authored Sep 04, 2025
```
Signed-off-by: nopperl <54780682+nopperl@users.noreply.github.com>
```
  2b30afa4
- [Model] Add pp support for hunyuan (#24212) · eafa8dcd
  Jiangyun Zhu authored Sep 04, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  eafa8dcd
- [Feature][Response API] Add streaming support for non-harmony (#23741) · 8f423e5f
  Kebe authored Sep 04, 2025
```
Signed-off-by: Kebe <mail@kebe7jun.com>
```
  8f423e5f
- [Attention] FlashAttn MLA (#14258) · 402759d4
  Lucas Wilkinson authored Sep 04, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
```
  402759d4
- [Bugfix] Fix Incremental Detokenization with `tokenizers == 0.22.0` (#24159) · 2c301ee2
  Fanli Lin authored Sep 04, 2025
```
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
Signed-off-by: Fanli Lin <fanli0116@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  2c301ee2
- [Attention][Platform] Refactor MLA to support Custom Op (#23332) · 3efb9f4d
  whx authored Sep 04, 2025
```
Signed-off-by: whx-sjtu <2952154980@qq.com>
```
  3efb9f4d
- [Core][Model] Terratorch backend integration (#23513) · 51d5e9be
  mgazz authored Sep 04, 2025
```
Signed-off-by: Michele Gazzetti <michele.gazzetti1@ibm.com>
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  51d5e9be
- [Model] Add MiDashengLM model support (#23652) · e7fc7001
  bingchen-mi authored Sep 04, 2025
```
Signed-off-by: chenbing8 <chenbing8@xiaomi.com>
Signed-off-by: bingchen-mi <chenbing8@xiaomi.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  e7fc7001
- [CPU] Refactor CPU unquantized linear (#24150) · 57b1ce94
  Li, Jiang authored Sep 04, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  57b1ce94
- Migrate ultravox inputs to TensorSchema (#23503) · cb55ad86
  Benji Beck authored Sep 03, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  cb55ad86
- [Refactor] Introduce basic Renderer for completion-style request (#24010) · 712b273f
  Flora Feng authored Sep 03, 2025
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  712b273f
- [Feature][Responses API]Support MCP tools with streaming mode + background mode (#23927) · a38f8bd5
  wuhang authored Sep 04, 2025
```
Signed-off-by: wuhang <wuhang6@huawei.com>
```
  a38f8bd5
03 Sep, 2025 17 commits
- Remove deprecated `PyNcclConnector` (#24151) · b5ee1e32
  Peter Pan authored Sep 04, 2025
```
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
```
  b5ee1e32
- [Feature][gpt-oss] Add support for num_cached_tokens and num_reasoning_tokens tracking (#23460) · 36c260da
  George Nagy II authored Sep 03, 2025
```
Signed-off-by: George Nagy II <george.nagy0969@gmail.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  36c260da
- [Bugfix][DP] DP distribution does not require ray[default] (#23822) · a43a3f17
  Kebe authored Sep 04, 2025
```
Signed-off-by: Kebe <mail@kebe7jun.com>
```
  a43a3f17
- [Feature][P/D]: Optimize NIXL Connector xfer Launch (#23887) · 6adaed42
  WeiQing Chen authored Sep 04, 2025
```
Signed-off-by: ycyaw66 <497410282@qq.com>
Co-authored-by: ycyaw66 <497410282@qq.com>
```
  6adaed42
- [Attention] Blackwell FP8 MLA support with CUTLASS_MLA backend (#23289) · a7423220
  Matthew Bonanni authored Sep 03, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  a7423220
- Migrate whisper inputs to TensorSchema (#23505) · 731a6940
  Benji Beck authored Sep 03, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  731a6940
- [Kernels] Overlap shared experts with send/recv (#23273) · e9b92dcd
  bnellnm authored Sep 03, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  e9b92dcd
- [V1] v1 engine + full CUDA graph support for PLaMo2 (#23998) · fa4311d8
  nopperl authored Sep 04, 2025
```
Signed-off-by: Hemmi Shinichi <shemmi@preferred.jp>
Signed-off-by: nopperl <54780682+nopperl@users.noreply.github.com>
Co-authored-by: Hemmi Shinichi <shemmi@preferred.jp>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>
```
  fa4311d8
- [Bugfix] Fixing division by zero in triton_attn if query_heads/kv_heads > 16 (#23424) · 6d80ae83
  Burkhard Ringlein authored Sep 03, 2025
```
Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
```
  6d80ae83
- [Model] Remove useless code from MiniMax implementation (#23982) · 6997a25a
  qscqesze authored Sep 03, 2025
```
Signed-off-by: QscQ <qscqesze@gmail.com>
Signed-off-by: qingjun <qingjun@minimaxi.com>
```
  6997a25a
- Support add_generation_prompt in embeddings endpoint with chat request (#23931) · 28f350e1
  Jakub Smid authored Sep 03, 2025
```
Signed-off-by: biba10 <jaksmid@seznam.cz>
```
  28f350e1
- [Misc] Clean up deadcode for legacy processing pipeline (#24153) · 9c99e487
  Isotr0py authored Sep 03, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  9c99e487
- [CI/Build] Serve images used by multimodal tests through local HTTP Server (#23907) · 70549c12
  dsinghvi authored Sep 03, 2025
```
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  70549c12
- [Nixl] Heterogeneous TP support FlashInfer (#20189) · f0c503f6
  Nicolò Lucchesi authored Sep 03, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  f0c503f6
- [distributed][rl] remove nccl cumem env var override (#24141) · f38035c1
  youkaichao authored Sep 03, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  f38035c1
- [BugFix] Fix routed_scaling_factor double mul for dots1 and glm4 MoE models (#24132) · 426cc862
  Yong Hoon Shin authored Sep 02, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  426cc862
- [Misc] Add check for dual_chunk_attention (#24070) · e81d4e69
  Jiangyun Zhu authored Sep 03, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  e81d4e69