Commits · ad344ef552ece428d12e04fbcb64b8b50768283b · OpenDAS / vllm_cscc

12 Aug, 2025 5 commits
- [gpt-oss] Small bug fixes for frontend (#22512) · ad344ef5
  Chen Zhang authored Aug 11, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  ad344ef5
- [gpt-oss] Fix mxfp4 support (#22700) · bbaf9e9c
  Chen Zhang authored Aug 11, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  bbaf9e9c
- Migrate MiniCPMVImageInputs to TensorSchema (#21939) · 46785034
  Benji Beck authored Aug 11, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  46785034
- Enable 4bit bnb prequant MOE (#21548) · 9b94d6ec
  Andy Chen authored Aug 11, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  9b94d6ec
- [gpt-oss] Support streaming in response API (#22431) · 95a935fc
  Chen Zhang authored Aug 11, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  95a935fc
11 Aug, 2025 17 commits
- Support more parallel styles in Transformers backend TP (#22651) · 458e74eb
  Harry Mellor authored Aug 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  458e74eb
- [BugFix] [Spec Decode] Remove LlamaForCausalLMEagle3 to fix CI (#22611) · 807d21b8
  22quinn authored Aug 11, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  807d21b8
- [Model] Pooling models default to using chunked prefill & prefix caching if supported. (#20930) · 84cf78ac
  wang.yuqi authored Aug 12, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  84cf78ac
- fix: NIXL connector transfers partial block to pass full multi-modal context (#21074) · 16fb668b
  GuanLuo authored Aug 11, 2025
```
Signed-off-by: GuanLuo <gluo@nvidia.com>
```
  16fb668b
- [Feature] Add `VLLM_USE_DEEP_GEMM_E8M0` Env to Control E8M0 Scale (#21968) · f7dcce7a
  Wentao Ye authored Aug 11, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  f7dcce7a
- [Misc] Further clean up some redundant config definitions (#22649) · 8e13d9fe
  Isotr0py authored Aug 12, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  8e13d9fe
- [Model] NemotronH Support (#22349) · 14a5d903
  danielafrimi authored Aug 11, 2025
```
Signed-off-by: Daniel Afrimi <danielafrimi8@gmail.com>
```
  14a5d903
- [Misc] Move jsontree to utils (#22622) · 951b0382
  Cyrus Leung authored Aug 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  951b0382
- [Docs] Add comprehensive CLI reference for all large `vllm` subcommands (#22601) · bc1d02ac
  Harry Mellor authored Aug 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  bc1d02ac
- [BUGFIX] KeyError 'layers.14.mlp.gate.g_idx' for Qwen3-MoE with GPTQ on ROCm (#22017) · 1e55dfa7
  JartX authored Aug 11, 2025
  
  1e55dfa7
- Support token_type_ids in V1 with less code changes (#21985) · 39052dbc
  Maximilien de Bayser authored Aug 11, 2025
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
```
  39052dbc
- [ROCm][AITER] Support AITER Rope ops in RotaryEmbedding Module. (#22521) · 9c97a1c3
  vllmellm authored Aug 11, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
  9c97a1c3
- [BugFix] Fix logits repetition penalty cuda check (#22592) · f919d4cb
  Eugene Cheah authored Aug 10, 2025
  
  f919d4cb
- [Misc][gpt-oss] guard import when triton kernel when not up to date (#22584) · afa5b7ca
  Zhewen Li authored Aug 10, 2025
```
Signed-off-by: zhewenli <zhewenli@meta.com>
```
  afa5b7ca
- [BugFix] Fix KVConnectorOutput TPU breakage (#22598) · 5898b135
  Nick Hill authored Aug 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  5898b135
- Migrate LlavaImageInputs to TensorSchema (#21770) · 06da44f0
  Benji Beck authored Aug 10, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  06da44f0
- Migrate LlavaNextVideoPixelInputs to TensorSchema (#21843) · a5549917
  Benji Beck authored Aug 10, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  a5549917
10 Aug, 2025 15 commits
- enable Docker-aware precompiled wheel setup (#22106) · d1af8b7b
  Doug Smith authored Aug 10, 2025
```
Signed-off-by: dougbtv <dosmith@redhat.com>
```
  d1af8b7b
- Remove redundant row_indices unsqueeze operation in MiniCPMO (#22528) · 8c50d62f
  ZiTian Zhao authored Aug 11, 2025
```
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
```
  8c50d62f
- Migrate LlavaNextImageInputs to TensorSchema (#21774) · b4e29167
  Benji Beck authored Aug 10, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  b4e29167
- Fix(benchmarks): allow multiple mm contents in OpenAI Chat Completion Benchmarks (#22534) · 65a7917b
  Breno Baldas Skuk authored Aug 10, 2025
```
Signed-off-by: breno.skuk <breno.skuk@hcompany.ai>
```
  65a7917b
- [Bugfix][Kernel] Support partial rotary embedding for MRoPE triton kernel (#22593) · b76753f0
  Isotr0py authored Aug 11, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  b76753f0
- Move `CacheConfig` from `config/__init__.py` to `config/cache.py` (#22586) · 8290d15d
  Harry Mellor authored Aug 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8290d15d
- [Docs] Fix warnings in docs build (#22588) · 00976db0
  Harry Mellor authored Aug 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  00976db0
- [Misc] Further refine type annotations in parallel state (#22499) · d411df02
  Cyrus Leung authored Aug 10, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  d411df02
- [Minor] Fix pre-commit error on main (#22579) · 7e8d6857
  Isotr0py authored Aug 10, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  7e8d6857
- Refactor sliding window configuration to Transformers best practice (#21927) · c4984839
  Harry Mellor authored Aug 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  c4984839
- [TPU] kv cache update kernel doesn't need to be padded slices to multiple of... · 2a84fb42
  Chengji Yao authored Aug 09, 2025
```
[TPU] kv cache update kernel doesn't need to be padded slices to multiple of num_slices_per_block (#22394)
Signed-off-by: Chengji Yao <chengjiyao@gmail.com>
Co-authored-by: Chengji Yao <chengjiyao@gmail.com>
```
  2a84fb42
- Improve fast_topk function with type hints and documentation (#22530) · 534c45b9
  ZiTian Zhao authored Aug 10, 2025
```
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
```
  534c45b9
- [Config] add "qwen" as a native eagle3 target supported model (#22333) · 3d7363e6
  Le Chen authored Aug 10, 2025
```
Signed-off-by: lechen <lecself@163.com>
Signed-off-by: LeChen <lecself@163.com>
```
  3d7363e6
- [oss] Init gpt-oss bf16 support (#22508) · 0c5254b8
  Jee Jee Li authored Aug 10, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  0c5254b8
- [V1] [Hybrid] Enable Full CUDA Graph (decode-only) for Mamba layers (#21401) · 61f67d8a
  Thomas Parnell authored Aug 10, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  61f67d8a
09 Aug, 2025 3 commits

[FEAT] [Performance] Add triton mrope to replace the torch code path (#22375) · 42172ad1
TJian authored Aug 09, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
42172ad1
[Bugfix] Fix basic models tests hanging due to mm processor creation (#22571) · fbd8595c
Isotr0py authored Aug 10, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
fbd8595c

[Model] Gemma3n MM (#20495) · 5a16fa61

Nicolò Lucchesi authored Aug 09, 2025


Signed-off-by: ShriKode <shrikode@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: ShriKode <shrikode@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.me>

5a16fa61