Commits · 1244948885e364b3103aa3b515ce66fa4d9955fa · OpenDAS / vllm_cscc

01 Oct, 2025 1 commit
- [Log] Optimize Log for FP8MOE (#25709) · 12449488
  Wentao Ye authored Sep 30, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  12449488
30 Sep, 2025 14 commits

Add explicit pooling classes for the Transformers backend (#25322) · a388252a

Harry Mellor authored Sep 30, 2025


Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

a388252a

[Llama4] [multimodal] Fix misplaced dtype cast of `cos_sin_cache` in... · 43b752c3

cjackal authored Oct 01, 2025


[Llama4] [multimodal] Fix misplaced dtype cast of `cos_sin_cache` in `Llama4VisionRotaryEmbedding` (#25889)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>

43b752c3

[Bug] Fix AttributeError: 'QKVParallelLinear' object has no attribute 'orig_dtype' (#25958) · e6a226ef
Wentao Ye authored Sep 30, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
e6a226ef
[Bugfix] Token type and position embeddings fail to be applied to `inputs_embeds` (#25922) · 9f1c4eca
Cyrus Leung authored Oct 01, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
9f1c4eca
[Bugfix] Fix accuracy issue of TRTLLM FP8 MOE and improve logging (#25895) · ef283548
Pavani Majety authored Sep 30, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
ef283548

[Bugfix][Model] Fix inference for Hunyuan dense models (#25354) · f4db5e6d

Anion authored Sep 30, 2025


Signed-off-by: anion <1005128408@qq.com>
Signed-off-by: Anion <123177548+Anionex@users.noreply.github.com>

f4db5e6d

[Kernel][Moe Configs] Add more tuned triton configs for ExpertsInt8 and FP8 (#25858) · 35fe398c
Asaf Joseph Gardin authored Sep 30, 2025
```
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
```
35fe398c
[Model] Move `vision_feature_select_strategy` into `resolve_visual_encoder_outputs` (#25938) · d7e34b42
Cyrus Leung authored Sep 30, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
d7e34b42
[Bugfix][Model]fix ernie45 moe gate&bias dtype to float32 (#25936) · ef6e0e71
CSWYF3634076 authored Sep 30, 2025
```
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
```
ef6e0e71

[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896) · fa7e254a

Yongye Zhu authored Sep 30, 2025


Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>

fa7e254a

[Model][Bugfix] Fix MiDashengLM audio encoder mask by removing incorrect `logical_not` (#25925) · 2e1b8bc2
zhoukz authored Sep 30, 2025
```
Signed-off-by: zhoukz <me@zhoukz.com>
```
2e1b8bc2
Move`VllmConfig` from `config/__init__.py` to `config/vllm.py` (#25271) · 61aedb5f
Harry Mellor authored Sep 30, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
61aedb5f

[Bug] Fix Weight Loading for Block FP8 Cutlass SM90 (#25909) · 89e4050a

Wentao Ye authored Sep 29, 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>

89e4050a

Test Prompt Embeds/LoRA compatibility and Enable LoRA Support for OPT Models (#25717) · 78a47f87
Andrew Sansom authored Sep 29, 2025
```
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
```
78a47f87

29 Sep, 2025 9 commits
- [Kernel] Chunk-aligned mamba2 (#24683) · fea3e476
  Thomas Parnell authored Sep 29, 2025
  
  fea3e476
- [Bugfix] Use correct key "ignore" for config.json non-quantized layers (#25706) · d5ab2851
  Lee Nau authored Sep 29, 2025
```
Signed-off-by: Lee Nau <lnau@nvidia.com>
```
  d5ab2851
- [Model] Remove MotifForCausalLM (#25866) · e61eb5e0
  Jee Jee Li authored Sep 30, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  e61eb5e0
- [Bugfix][Speculative Decoding] Fix Eagle3 quantization config issue (#25883) · 145ac733
  Rahul Tuli authored Sep 29, 2025
```
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
```
  145ac733
- [Model][Bugfix] Fix issues in MiDashengLM implementation for quantized models (#25854) · 8616300a
  zhoukz authored Sep 29, 2025
```
Signed-off-by: zhoukz <me@zhoukz.com>
```
  8616300a
- [Misc] Remove more `get_input_embeddings_v0` (#25857) · 1b67b046
  Cyrus Leung authored Sep 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  1b67b046
- [V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331) · bd51f78e
  Isotr0py authored Sep 29, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
```
  bd51f78e
- [Bugfix] Fallback ViT attn backend to SDPA for blackwell (#25851) · 65ecb4f1
  Roger Wang authored Sep 28, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  65ecb4f1
- Add Phi4FlashForCausalLM to _PREVIOUSLY_SUPPORTED_MODELS (#25832) · 219cfbe7
  Thomas Parnell authored Sep 29, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  219cfbe7
28 Sep, 2025 4 commits
- [Bugfix] fix Qwen3VLMoe load when pp > 1 (#25838) · 471997ad
  JJJYmmm authored Sep 29, 2025
```
Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com>
Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com>
```
  471997ad
- Update GLM-4.5 Doc transformers version (#25830) · b1ded114
  Yuxuan Zhang authored Sep 28, 2025
```
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
```
  b1ded114
- [VLM] Update Qwen3-VL max_num_video_tokens calculation for configurable video profiling (#25557) · 0efd540d
  Isotr0py authored Sep 28, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  0efd540d
- [Bugfix] Fix Qwen3-VL regression from #24982 (#25814) · 61447540
  Roger Wang authored Sep 27, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  61447540
27 Sep, 2025 8 commits
- [Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982) · a5354b3e
  Tyler Michael Smith authored Sep 27, 2025
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
  a5354b3e
- [Bugfix] Fix triton import precommit failure (#25803) · f9df8b4a
  Tyler Michael Smith authored Sep 27, 2025
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
  f9df8b4a
- Fix GPTQ model loading in Transformers backend (#25770) · ec152c87
  Harry Mellor authored Sep 27, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  ec152c87
- [Bugfix] Merge MM embeddings by index instead of token IDs (#16229) · 27d7638b
  Cyrus Leung authored Sep 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  27d7638b
- [Bugfix] Add missing `image_size` for phi4_multimodal (#25796) · 17617398
  Xiaohan Zou authored Sep 27, 2025
  
  17617398
- [CI/Build] Consolidate model loader tests and requirements (#25765) · d346ec69
  Cyrus Leung authored Sep 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  d346ec69
- [Bugfix] Allow Only SDPA Backend for ViT on B200 for Qwen3-VL (#25788) · c242c980
  Wentao Ye authored Sep 26, 2025
  
  c242c980
- [Multimodal][Speculative Decoding]Eagle Eagle3 mm support, enablement on qwen2.5vl (#22872) · f1d53d15
  WeiQing Chen authored Sep 27, 2025
```
Signed-off-by: Junhong <liujunhong11@huawei.com>
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
Co-authored-by: Junhong <liujunhong11@huawei.com>
Co-authored-by: LJH-LBJ <98734602+LJH-LBJ@users.noreply.github.com>
```
  f1d53d15
26 Sep, 2025 4 commits

Kernel-override Determinism [1/n] (#25603) · dc48ba0c
Bram Wasti authored Sep 26, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
```
dc48ba0c
[CI] Add E2E Blackwell Quantized MoE Test (#25723) · f708bd49
Michael Goin authored Sep 26, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
f708bd49

Eagle3 that supports the Minicpm3 model (#24243) · 33f6aaf9

阿丹(adan) authored Sep 27, 2025


Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: liudan <adan@minicpm.com>
Co-authored-by: liudan <liudan@qq.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>

33f6aaf9

[Quantization] Add field to skip unquantized modules for GPTQ config (#25455) · d4d98998
Isotr0py authored Sep 26, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
d4d98998