Commits · 030fc4491465d361e4bed626d76c184f8a7d8a07 · OpenDAS / vllm_cscc · GitLab

25 Dec, 2025 2 commits
- use the same stream for cuda graph catpure and replay for NCCL (#29207) · 030fc449
  Amir Samani authored Dec 25, 2025
```
Signed-off-by: Amir Samani <asamani@nvidia.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  030fc449
- [Frontend] add FunctionGemma tool parser support (#31218) · ba25a659
  Mark Gatere authored Dec 25, 2025
```
Signed-off-by: gateremark <gateremg@gmail.com>
```
  ba25a659
24 Dec, 2025 23 commits
- [Perf] Add skip_clone to SamplingParams for internal request handling (#31041) · bc5ef333
  Michael Goin authored Dec 24, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  bc5ef333
- [Chore][1/2] Drop `v0.14` deprecations (#31285) · 09dc7c69
  Cyrus Leung authored Dec 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  09dc7c69
- [Bugfix] Remove dead `block_quant_to_tensor_quant` function (#31294) · 506eb0f4
  ゆり authored Dec 25, 2025
```
Co-authored-by: yurekami <yurekami@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  506eb0f4
- [cli] complete vllm cli help message (#31226) · 5d930896
  Ning Xie authored Dec 24, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  5d930896
- [Bugfix][Hardware][AMD] Fix FP8 dtype in silu_mul quantization (#31179) · 66c98874
  Kevin McKay authored Dec 24, 2025
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  66c98874
- [Chore] Remove unused `noqa`s (#31263) · aa3868ec
  Cyrus Leung authored Dec 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  aa3868ec
- [Bugfix] Fix `max_model_len="auto"` handling (#31260) · 7adeb4bf
  Cyrus Leung authored Dec 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  7adeb4bf
- [Model] Introduce verify_and_update_model_config for VerifyAndUpdateConfig. (#31131) · bd89ce16
  wang.yuqi authored Dec 24, 2025
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
```
  bd89ce16
- [Bugfix][ROCm] Fix load issue on deepseek quark quantization when shared expert enabled (#31261) · b41aeb34
  Pleaplusone authored Dec 24, 2025
```
Signed-off-by: ganyi <ygan@amd.com>
```
  b41aeb34
- [CI/Build] Ignore data_parallel_size_local (#30281) · ddfac703
  Ryan Rock authored Dec 24, 2025
```
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
```
  ddfac703
- [ROCm][CI] Fix entrypoints tests and Python-only installation test on ROCm (#28979) · 0247a91e
  Andreas Karatzas authored Dec 24, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  0247a91e
- Add `--max-model-len auto` to auto-fit context to available memory (#29431) · 8ee90c83
  Michael Goin authored Dec 24, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  8ee90c83
- [XPU] Remove distributed_executor_backend check (#30760) · 471ddb99
  sihao_li authored Dec 24, 2025
```
Signed-off-by: sihao.li <sihao.li@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  471ddb99
- [Qwen3-Omni] fixed _get_feat_extract_output_lengths function (#31007) · bb24592d
  Xiong Wang authored Dec 24, 2025
```
Signed-off-by: Xiong Wang <wangxiongts@163.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  bb24592d
- [Bugfix][ROCm][Dynamo][DS 3.1][FP8] fix unsupported hasattr call when Dynamo... · dabff12e
  zejunchen-zejun authored Dec 24, 2025
```
[Bugfix][ROCm][Dynamo][DS 3.1][FP8] fix unsupported hasattr call when Dynamo tracing for ROCm device (#31149)
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>
```
  dabff12e
- Revert "[bench] Support common prefix len config (for decode-only bench)" (#31240) · 3bb95619
  Ming Yang authored Dec 23, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  3bb95619
- [ROCm][CI][Bugfix] Fix Siglip2 rotary embedding dispatch and InternVL video test tolerance (#31235) · e42894f5
  Andreas Karatzas authored Dec 23, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  e42894f5
- [Bug] Fix `Number of dimensions of tensors must match.` for Deepseek V3.2 (#31160) · 76e6a951
  Wentao Ye authored Dec 23, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  76e6a951
- [P/D] Mooncake connector support more protocols (#30133) · 8b59753c
  Chao Lei authored Dec 24, 2025
```
Signed-off-by: LCAIZJ <leichao139636@163.com>
```
  8b59753c
- [KVEvent] User request.block_hash for parent block_hash (#30544) · 538e830c
  Chen Zhang authored Dec 23, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
Co-authored-by: Yifan Qiao <yifanqiao@berkeley.edu>
```
  538e830c
- [Misc] Remove unused custom ops `copy_blocks` and `copy_blocks_mla` (#30967) · 4ed11105
  rongfu.leng authored Dec 24, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  4ed11105
- [Bugfix] Enable `dynamic_dims` for different embeds shape (#31223) · dd424571
  Cyrus Leung authored Dec 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  dd424571
- [Chore] Simplify logic of `_execute_mm_encoder` (#31222) · ca6a95ba
  Cyrus Leung authored Dec 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ca6a95ba
23 Dec, 2025 15 commits
- [ROCm][Bugfix] Fix RuntimeError in MMEncoderAttention by replacing .view() with .reshape() (#31203) · bfa2c0bb
  Andreas Karatzas authored Dec 23, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  bfa2c0bb
- [Core] Add a random suffix to frontend-provided request IDs (#27987) · f7900686
  Mark McLoughlin authored Dec 23, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  f7900686
- [Mamba] - Consolidate Mambas Attention Logic (#28133) · 34916ae3
  Asaf Joseph Gardin authored Dec 23, 2025
  
  34916ae3
- Use helper function instead of looping through attribute names (#29788) · c016c95b
  Harry Mellor authored Dec 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  c016c95b
- Only patch `original_max_position_embeddings` for Transformers v4 (#31214) · 1339878e
  Harry Mellor authored Dec 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  1339878e
- Fix edge case Mistral tool parser (#30724) · 38c361f9
  Joachim Studnia authored Dec 23, 2025
```
Signed-off-by: Joachim Studnia <joachim@mistral.ai>
Signed-off-by: Joachim Studnia <studniajoachim@gmail.com>
Signed-off-by: juliendenize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: juliendenize <julien.denize@mistral.ai>
Co-authored-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
```
  38c361f9
- [Misc] Introduce `encode_*_url` utility function (#31208) · bb62dda2
  Cyrus Leung authored Dec 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  bb62dda2
- adapt voxtral (#31095) · 3faa8bee
  Patrick von Platen authored Dec 23, 2025
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
```
  3faa8bee
- Add util function for checking nesting of rope parameters (#31146) · b10d47e0
  Harry Mellor authored Dec 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  b10d47e0
- [OpenAI] Add parameter metadata to validation errors (#30134) · 769f27e7
  R3hankhan authored Dec 23, 2025
```
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
```
  769f27e7
- [Frontend] Support using chat template as custom score template for reranking models (#30550) · 23daef54
  Jakub Zakrzewski authored Dec 23, 2025
```
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  23daef54
- [Bugfix] Fix MoE LoRA bin/pt loading (#31161) · 27c6c2f9
  Jee Jee Li authored Dec 23, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  27c6c2f9
- Correct position of docstring of class attributes (#31209) · 73cfb7a7
  Weida Hong authored Dec 23, 2025
```
Signed-off-by: Weida Hong <wdhongtw@google.com>
```
  73cfb7a7
- [ROCm][FEAT] Support AITER RMSNorm quantization fusion pass (#26575) · f32cfd7d
  vllmellm authored Dec 23, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  f32cfd7d
- [Bugfix] Fix Jais2ForCausalLM (#31198) · 6b16fff0
  Jee Jee Li authored Dec 23, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  6b16fff0