Commits · 430dd4d9eb7e342e28012351df06d93892f86741 · OpenDAS / vllm_cscc

26 Nov, 2025 9 commits
- [Attention] Remove imports from `vllm/attention/__init__.py` (#29342) · 430dd4d9
  Matthew Bonanni authored Nov 26, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  430dd4d9
- [refactor] CTConfig methods to static/class methods (#28870) · e6031295
  HDCharles authored Nov 26, 2025
```
Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  e6031295
- [Perf] Optimize batch invariant BMM, 18.1% Throughput improvement, 10.7% TTFT improvement (#29345) · 0b0aa874
  Wentao Ye authored Nov 26, 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>
```
  0b0aa874
- Revert "[Bugfix] Fix GPT-OSS AR+NORM fusion (#28841)" (#29483) · 70d5953f
  Huamin Li authored Nov 26, 2025
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
  70d5953f
- Fix TeleChatForCausalLM not register issue (#29473) · bb706d60
  Yejing Lai authored Nov 26, 2025
```
Signed-off-by: Lai, Yejing <yejing.lai@intel.com>
```
  bb706d60
- [Bugfix] Fix handling of image embeds in models (#29480) · e30859df
  Cyrus Leung authored Nov 26, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  e30859df
- [Misc] Allow LM only loading for Pixtral (#29451) · 452a7c9f
  Roger Wang authored Nov 26, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  452a7c9f
- [Kernel] Use pre-allocated output buffer for triton kernel fused_experts (#29219) · 53d7f1f6
  Xin Yang authored Nov 25, 2025
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  53d7f1f6
- [Misc] Add backup hash algorithm for FIPS constrained environments (#28795) · 56531b79
  George D. Torres authored Nov 25, 2025
```
Signed-off-by: George D. Torres <gdavtor@gmail.com>
Signed-off-by: George D. Torres <41129492+geodavic@users.noreply.github.com>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
```
  56531b79
25 Nov, 2025 11 commits

Change warning logs to debug for unimplemented MXFP4 Linear/Attention (#29441) · 7df02897
Michael Goin authored Nov 25, 2025
```
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
7df02897
Fix RoPE related failures in Transformers nightly tests (#29333) · 0353d2e1
Harry Mellor authored Nov 25, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
0353d2e1
[Hybrid Allocator] Support KV cache groups with different block_size (#29143) · 48ddb02b
Yifan Qiao authored Nov 25, 2025
```
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
```
48ddb02b
[Kernel] Add NVFP4 MoE CUTLASS support for SM120 (#29242) · e5020986
Michael Goin authored Nov 25, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
```
e5020986

[Feature]: Improve GGUF loading from HuggingFace user experience like repo_id:quant_type (#29137) · 794029f0

Injae Ryou authored Nov 25, 2025


Signed-off-by: Injae Ryou <injaeryou@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

794029f0

[Bugfix] Fix GPT-OSS AR+NORM fusion (#28841) · 6330f947
elvischenv authored Nov 25, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
6330f947
[fix][cpu] Use a SwigluOAI impl which supports interleaved gate-up wei (#29273) · 98caeadd
Fadi Arafeh authored Nov 25, 2025
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
98caeadd

[Model] Add HunyuanOCR support (#29327) · 92effb07

Isotr0py authored Nov 25, 2025


Signed-off-by: manayang <jackmanayang@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: sergeywang <sergeywang@tencent.com>
Co-authored-by: manayang <jackmanayang@gmail.com>
Co-authored-by: manayang <manayang@tencent.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

92effb07

[Perf] Disable DeepGEMM MoE by default when TP=8 is used (#29346) · 6f1355a1
Michael Goin authored Nov 24, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
6f1355a1

[Spec Decode] Add support for EAGLE3 heads that do not use_aux_hidden_states (#27688) · 5f9679a4

Hanjie Qiu authored Nov 24, 2025


Signed-off-by: hjjq <hanjieq@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

5f9679a4

[UX] Raise error for attn backend of batch invariant (#29348) · 699bca76
Wentao Ye authored Nov 24, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
699bca76

24 Nov, 2025 9 commits
- [Bugfix] Only use triton_kernels for MXFP4 on SM90 and SM100 (#29339) · c17610e2
  Michael Goin authored Nov 24, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  c17610e2
- [XPU]fix Kimi-VL-A3B-thinking on xpu (#29309) · 3cfa63ad
  Yan Ma authored Nov 25, 2025
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  3cfa63ad
- [Multimodal][Qwen3 Omni] Make Qwen3 Omni work with audio-in-video inputs in V1 engine. (#27721) · 839c6b7b
  Chenheli Hua authored Nov 24, 2025
```
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  839c6b7b
- [MoE][Refactor] Make select_experts a non-static method (#29067) · 8f066146
  bnellnm authored Nov 24, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  8f066146
- Add option to use unbacked, and backed size obl dynamic shapes for more sounds... · 7a228b53
  Laith Sakka authored Nov 24, 2025
```
Add option to use unbacked, and backed size obl dynamic shapes for more sounds compilation. (#26199)
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
  7a228b53
- [Bugfix][Rocm] Fix shared expert weight loading failure in DeepSeek-MTP (#27563) · 8005e606
  杰兮 authored Nov 24, 2025
```
Signed-off-by: zhyajie <yajizhan@amd.com>
Co-authored-by: zhyajie <yajizhan@amd.com>
```
  8005e606
- [Core] Deprecate `xformers` (#29262) · 0ff70821
  Roger Wang authored Nov 23, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  0ff70821
- [Model] Add OpenCUA-7B support (#29068) · 30854783
  Zero authored Nov 24, 2025
```
Signed-off-by: lim4349 <rockmanzero@naver.com>
Signed-off-by: Zero <rockmanzero@naver.com>
Co-authored-by: Cloud User <ubuntu@a100-80g-4.novalocal>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  30854783
- [LoRA] Optimize 3D MoE logic (#29222) · 1073ba68
  Jee Jee Li authored Nov 24, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  1073ba68
23 Nov, 2025 1 commit

[Fix] Add SM check to flashinfer MOE backend (#29144) · 5f96c00c

jiahanc authored Nov 22, 2025


Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

5f96c00c

22 Nov, 2025 8 commits
- chore: add RTX_PRO_6000 GLM4.6-FP8 kernel tuning (#29240) · f55c76c2
  Federico authored Nov 22, 2025
  
  f55c76c2
- Fix EVS crash when using `video_embeds` inputs in Qwen2.5-VL (#29232) · d84d8f44
  ZiTian Zhao authored Nov 22, 2025
```
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  d84d8f44
- [Misc] Fix pre-commit (#29238) · ae668183
  Cyrus Leung authored Nov 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ae668183
- [tiny] Remove unsupported TRITON_MLA backend from batch invariance (#28832) · 5f7209a7
  Bram Wasti authored Nov 22, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
Signed-off-by: Bram Wasti <bwasti@fb.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  5f7209a7
- Fix: Resolve circular import in model_loader/utils.py (#29189) · 6965a392
  Nandan Vallamdasu authored Nov 22, 2025
```
Signed-off-by: nandan2003 <nandan.vallamdasu@outlook.com>
Signed-off-by: Nandan Vallamdasu  <nandan.vallamdasu@outlook.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  6965a392
- Handle triton kernel import exception (#29062) · 988ee66b
  jinghanhu authored Nov 22, 2025
  
  988ee66b
- Add fused MoE config for H200 E160 N192 fp8 (#29182) · 052950e5
  FlintyLemming authored Nov 22, 2025
```
Signed-off-by: FlintyLemming <admin@flinty.moe>
```
  052950e5
- [Model][Qwen3VL] Tune Triton w8a8 block fp8 kernel for L40s (#29217) · d045e22d
  Lukas Geiger authored Nov 22, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  d045e22d
21 Nov, 2025 2 commits

[BugFix] EPLB + B200 + DeepGEMM : Handle column-major scales tensor (#29162) · 3137991f
Varun Sundar Rabindranath authored Nov 21, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
3137991f

Default model load/config/tokenizer to `mistral` format if relevant files exist (#28659) · 57430fc9

Julien Denize authored Nov 21, 2025


Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

57430fc9