Commits · c4d62618ca7cf8507c1e357fa1180fb162c670fa · OpenDAS / vllm_cscc

06 Dec, 2025 2 commits

Fix AWQ MoE marlin check issue in marlin_utils.py for AMD backend (#30102) · c4d62618
yuttian1 authored Dec 06, 2025
```
Signed-off-by: yuttian1 <yuttian@amd.com>
```
c4d62618

[CI/Build][AMD][Quantization] Fix test_int8_kernel.py by updating int8_utils... · dc839ad0

rasmith authored Dec 05, 2025


[CI/Build][AMD][Quantization] Fix test_int8_kernel.py by updating int8_utils to use hip.libdevice.round (#30151)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>

dc839ad0

05 Dec, 2025 7 commits

[Bug] Fix vLLM config is not set error (#29999) · 7b5575fa
Wentao Ye authored Dec 05, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
7b5575fa
[Bugfix][llama4_eagle] Fix missing 'lm_head' attribute (#29926) · 962d7038
Divakar Verma authored Dec 05, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
962d7038

[Attention][UX][1/N] Add AttentionConfig and change attention env vars to CLI arguments (#26315) · 66e674cd

Matthew Bonanni authored Dec 05, 2025

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

66e674cd

[Compressed Tensors] Add XPU `wNa16` support (#29484) · 0d8a7d8a
Yi Liu authored Dec 05, 2025
```
Signed-off-by: yiliu30 <yi4.liu@intel.com>
```
0d8a7d8a
[ROCm][MXFP4] Infer w4a4 quant method in rocm aiter fused moe (#29775) · 3628bcaa
Zhiwei authored Dec 05, 2025
```
Signed-off-by: ZhiweiYan-96 <zhiwei.yan@amd.com>
```
3628bcaa

[Frontend][Model] Add 'float16' to possible mamba cache dtype values, override... · 6038b1b0

amitz-nv authored Dec 05, 2025


[Frontend][Model] Add 'float16' to possible mamba cache dtype values, override mamba SSM cache dtype value for NemotronH (#29978)
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>

6038b1b0

[Perf] Enable separate shared_experts stream only for CUDA (#30085) · 4470ee2f
Alexander Matveev authored Dec 04, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
4470ee2f

04 Dec, 2025 9 commits
- Access `partial_rotary_factor` from `rope_parameters` (#29966) · e10c84e0
  Harry Mellor authored Dec 04, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e10c84e0
- [Bugfix] Fix FP8 MoE LoRA (#29890) · 652ba93d
  Jee Jee Li authored Dec 05, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  652ba93d
- support qwen3-vl handle requests with embeddings (#30037) · 6dcb07f6
  Tao Yun authored Dec 05, 2025
```
Signed-off-by: taoyun <1069423820@qq.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  6dcb07f6
- [Chore] Deprecate `merge_by_field_config` arg (#30035) · b286a311
  Cyrus Leung authored Dec 05, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b286a311
- Delete HF version of Phi 4 MM (#30049) · 9998ea5b
  Harry Mellor authored Dec 04, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  9998ea5b
- [Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145) · 74c4d80c
  wang.yuqi authored Dec 04, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  74c4d80c
- [Misc] Move functions into `PoolingMetadata` (#30027) · 68eb5c8d
  Cyrus Leung authored Dec 04, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  68eb5c8d
- [ROCm] [Bugfix] `compute_attn_mask_seqlen` for qwen3 omni (#29974) · 3f1b0373
  TJian authored Dec 04, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  3f1b0373
- [Misc] Various cleanups for MM input processing (#29970) · 9ae2f603
  Cyrus Leung authored Dec 04, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9ae2f603
03 Dec, 2025 5 commits

[Kernels] Remove BatchedTritonOrDeepGemmExperts and default fallback to Triton (#29929) · 2902c348

bnellnm authored Dec 03, 2025


Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: bnellnm <49004751+bnellnm@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

2902c348

[Performance][DP/EP] Add silu_mul_per_token_group_quant_fp8_colmajor kernel (#29470) · 19bee6d1

Varun Sundar Rabindranath authored Dec 03, 2025

Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

19bee6d1

[refactor] CTMoEMethods to use QuantizationArgs (#28871) · b294e28d

HDCharles authored Dec 03, 2025


Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

b294e28d

[Bugfix][Quantization] Support BF16 tensors on GGUF (#29948) · 42c19496
Tsukasa OI authored Dec 03, 2025
```
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
```
42c19496

[Bugfix] Fix incorrect `image_grid_thw` rank for HunyuanOCR from missing... · a21cd9ed

Isotr0py authored Dec 03, 2025


[Bugfix] Fix incorrect `image_grid_thw` rank for HunyuanOCR from missing `merge_by_field_config=True` (#29950)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

a21cd9ed

02 Dec, 2025 12 commits

[BUGFIX] llama_4_scaling wrongly passed to DeepseekAttention (#29908) · 5e5646e2
Julien Denize authored Dec 02, 2025
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
5e5646e2
Fix some more Transformers nightly tests (#29872) · 6fc5841d
Harry Mellor authored Dec 02, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
6fc5841d
feat(model): Add BitsAndBytes quantization support for Qwen3-Omni-MoE (#29896) · a2b053dc
Navanit Dubey authored Dec 03, 2025
```
Signed-off-by: navanit-git <navanitdubey@gmail.com>
```
a2b053dc
[Attention][CUDAGraph] Remove CG padding from attention backends (#29352) · 1d93f116
Matthew Bonanni authored Dec 02, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
1d93f116

[Bugfix] Fix incorrect channel order for idefics3 in edge case (#29881) · 0ec84221

Isotr0py authored Dec 03, 2025

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

0ec84221

[Bugfix] Fix DeepSeek R1 MTP weight loading (#29545) · 51c57b51

Matthew Bonanni authored Dec 02, 2025


Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

51c57b51

[Chore] Use `tokenizer.encode` and `tokenizer.decode` directly (#29851) · 68ffbca7
Cyrus Leung authored Dec 02, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
68ffbca7

Add Mistral Large 3 and Ministral 3 (#29757) · d8c6210e

Julien Denize authored Dec 02, 2025


Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Mickael Seznec <mickael@mistral.ai>

d8c6210e

Fix some Transformers nightly tests (#29802) · f5b0846b
Harry Mellor authored Dec 02, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
f5b0846b
[Chore] Move tokenizer initialization methods (#29793) · 653591d5
Cyrus Leung authored Dec 02, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
653591d5
Add missing return in _check_vllm_model_embed_input_ids (#29834) · f441d36c
Johnny Yang authored Dec 01, 2025
```
Signed-off-by: Johnny Yang <johnnyyang@google.com>
```
f441d36c

[ROCm] Fallback pytorch GELU with tanh approximation to GELU() (#29244) · 4b409249

Divakar Verma authored Dec 01, 2025

Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Signed-off-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

4b409249

01 Dec, 2025 3 commits

[Frontend] add 'verbose_json' and 'timestamp' feature on Whisper Transcription/Translation (#24209) · 092bb73b
sangbumlikeagod authored Dec 02, 2025
```
Signed-off-by: sangbumlikeagod <oironese@naver.com>
Signed-off-by: sangbumlikeagod <98077576+sangbumlikeagod@users.noreply.github.com>
```
092bb73b
[XPU] Fix AWQ skipped layer detection in IPEX quantization (#29774) · f37e8938
Fanli Lin authored Dec 01, 2025
```
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
```
f37e8938

[MoE] CuteDSL MoE with Nvfp4 DeepEP dispatch (#27141) · f72a817b

Shu Wang authored Nov 30, 2025


Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: root <root@umbriel-b200-017.ipp4a1.colossus.nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

f72a817b

30 Nov, 2025 2 commits
- [Misc]Remove redundant hidden_size property in ModelConfig (#29749) · 21c26279
  Xingyu Liu authored Dec 01, 2025
```
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  21c26279
- [Feat] Support non-gated activations in NVFP4 modelopt path (#29004) · 39d28108
  Omer Ullman Argov authored Nov 30, 2025
  
  39d28108