Commits · 302ef403a2305e9158064f8e386d1b5284d12cb2 · OpenDAS / vllm_cscc · GitLab

15 Oct, 2025 15 commits
- [DSA][MLA] Tiny refactor on DeepSeek to make it reusable for different backends (#26656) · 302ef403
  Mengqing Cao authored Oct 15, 2025
```
Signed-off-by: MengqingCao <cmq0113@163.com>
```
  302ef403
- [Bugfix][Multi Modal] Fix incorrect Molmo token processing (#26873) · 8865da15
  sangho.lee authored Oct 15, 2025
```
Signed-off-by: sanghol <sanghol@allenai.org>
```
  8865da15
- [Graph Partition] pass tests for decorator (#26831) · f0862eae
  Boyuan Feng authored Oct 14, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  f0862eae
- [Bugfix] Fix qwen3-omni audio truncation issue (#26815) · 8c851f6d
  Isotr0py authored Oct 15, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  8c851f6d
- [BugFix] Patch inductor partitioning logic (#26735) · 7cfa420f
  Angela Yi authored Oct 14, 2025
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  7cfa420f
- [Feature] default --extra-body param to disable thinking in vllm bench serve (#26784) · a27b288e
  rongfu.leng authored Oct 15, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  a27b288e
- [CI/Build][Bugfix] fix qutlass cmake error when set QUTLASS_SRC_DIR (#26773) · e471d7ca
  zhrrr authored Oct 15, 2025
```
Signed-off-by: izhuhaoran <izhuhaoran@qq.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  e471d7ca
- [Docs] Move build.inc into arm.inc (#26862) · c43ca825
  Michael Yao authored Oct 15, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  c43ca825
- [Model] Add DeepSeek-V3.1 reasoning parser (split from PR #24972) (#25589) · 85a65e7f
  Tao Hui authored Oct 15, 2025
```
Signed-off-by: taohui <taohui3@gmail.com>
Signed-off-by: Tao Hui <taohui3@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  85a65e7f
- [Bugfix] Fixes prefix-repetition benchmark script (#26828) · a2986b3e
  kourosh hakhamaneshi authored Oct 14, 2025
```
Signed-off-by: Kourosh Hakhamaneshi <Kourosh@anyscale.com>
```
  a2986b3e
- [Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change ... · 96b9aa5a
  Morrison Turnansky authored Oct 14, 2025
```
[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change  compilation level to compilation mode, deprecation compilation level (#26355)
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  96b9aa5a
- Disable FlashInfer sampler by default (#26859) · e66d787b
  Michael Goin authored Oct 14, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  e66d787b
- [BUGFIX][NIXL] quick fix for 'assert self.connector_worker is not None' in... · bfad142e
  Chendi.Xue authored Oct 14, 2025
```
[BUGFIX][NIXL] quick fix for 'assert self.connector_worker is not None' in get_kv_connector_stats (#26851)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  bfad142e
- [Bugfix]fix Qwen3 xml tool parser (#26345) · 93546600
  Zhikaiiii authored Oct 15, 2025
```
Signed-off-by: Zhikaiiii <1658973216@qq.com>
```
  93546600
- [Core][Easy] Use envs.__getattr__ for all Unify to environment variable access (#26810) · 07ca70af
  Jialin Ouyang authored Oct 14, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  07ca70af
14 Oct, 2025 25 commits
- [torch.compile] Fix tests for torch==2.9 inductor partition (#26116) · 2dcd12d3
  Luka Govedič authored Oct 14, 2025
```
Signed-off-by: ProExpertProg <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
```
  2dcd12d3
- [WideEP][P/D] Add usage stats for DP+EP and KV Connector (#26836) · 579d2e54
  Tyler Michael Smith authored Oct 14, 2025
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
  579d2e54
- [frontend][gptoss] Add per turn stats into Harmony Context (#25061) · 0512c04a
  Ye Hu authored Oct 14, 2025
```
Signed-off-by: lacora <hyelacora@gmail.com>
Co-authored-by: Ye Hu <yehu@fb.com>
```
  0512c04a
- [CI Failure] Fix torchao dep failure for Quantization Test (#26824) · 7e0ef408
  Michael Goin authored Oct 14, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  7e0ef408
- [Core] Streamline some structured output related code (#26737) · 4aed506b
  Nick Hill authored Oct 14, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  4aed506b
- remove attn output view kernel (#26680) · a86b4c58
  Boyuan Feng authored Oct 14, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
Signed-off-by: Boyuan Feng <fby.1994@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  a86b4c58
- [Minor] Group async_scheduling related fields in model runner init (#26736) · ff4810ba
  Nick Hill authored Oct 14, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  ff4810ba
- fix: response_format for completion (#23212) · 9d696492
  Nan Qin authored Oct 14, 2025
```
Signed-off-by: Nan2018 <qinnanjoshua@gmail.com>
```
  9d696492
- Added MoE configs for llama 4, H200 device with tp=4/8 tuning (#26837) · 0e658189
  Dhruvil Bhatt authored Oct 14, 2025
```
Signed-off-by: Dhruvil Bhatt <bhattdbh@amazon.com>
```
  0e658189
- [Perf] Cache vllm.env.__getattr__ result to avoid recomputation (#26146) · 380f1752
  Jialin Ouyang authored Oct 14, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  380f1752
- Notice for deprecation of AutoAWQ (#26820) · b92ab3de
  HDCharles authored Oct 14, 2025
```
Signed-off-by: HDCharles <39544797+HDCharles@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  b92ab3de
- [Core] Reuse empty block lists whenever possible in KVCacheBlocks to mitigate GC costs (#24964) · acaa2c0a
  Jialin Ouyang authored Oct 14, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  acaa2c0a
- [Attention][Spec Decode] FlashMLA spec decode support (#26541) · 82af928c
  Matthew Bonanni authored Oct 14, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  82af928c
- llama4_vision_rope: add HIP override to accept (q, k) and avoid (positions, q, k) mismatch (#26790) · 87efc681
  Huamin Li authored Oct 14, 2025
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
  87efc681
- [CI Failure] Fix tests with missing TinyLlama-1.1B-Chat-v1.0-FP8-e2e (#26816) · c3a722fc
  Michael Goin authored Oct 14, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  c3a722fc
- [Kernel][MoE] Add MoE tunings for GLM 4.6-FP8 and GLM 4.5 Air on NVidia B200 (#26818) · aba48f7d
  Ze'ev Klapow authored Oct 14, 2025
  
  aba48f7d
- [CI] Raise VLLM_MAX_SIZE_MB to 500 due to failing Build wheel - CUDA 12.9 (#26722) · 04b5f980
  Michael Goin authored Oct 14, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  04b5f980
- Update coveragerc and add codecov.yml for path fixes (#26435) · efc8f7d8
  Reza Barazesh authored Oct 14, 2025
```
Signed-off-by: Reza Barazesh <rezabarazesh@meta.com>
```
  efc8f7d8
- [Config] Remove Unused Environment Variable `VLLM_DISABLE_PAD_FOR_CUDAGRAPH` (#26743) · 6d87a283
  Wentao Ye authored Oct 14, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  6d87a283
- Revert "[issues template] Encourage the author implement their own ideas" (#26814) · e6cdbd67
  wang.yuqi authored Oct 14, 2025
  
  e6cdbd67
- [Feature][Responses API] Stream Function Call - harmony (#24317) · df850c49
  Chauncey authored Oct 14, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  df850c49
- [KVConnector][Metrics] Aggregate scheduler-side KVConnectorStats (#26046) · 720394de
  Qier Li authored Oct 14, 2025
```
Signed-off-by: Qier Li <kevin44036@gmail.com>
```
  720394de
- [issues template] Encourage the author implement their own ideas (#26671) · 88a49745
  wang.yuqi authored Oct 14, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  88a49745
- use combo kernel to fuse qk-norm and qk-rope (#26682) · ca683a2a
  Boyuan Feng authored Oct 14, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  ca683a2a
- Adjusted the model order of the model registration file (#26798) · e9f1b8c9
  汪志鹏 authored Oct 14, 2025
```
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
```
  e9f1b8c9