Commits · e2de455c349df8385b18fe447beb6325dcb6af9c · OpenDAS / vllm_cscc · GitLab

11 Jul, 2025 5 commits
- [Feature] Integrate SM100 DeepGEMM support (#20087) · e2de455c
  Wentao Ye authored Jul 10, 2025
  
  e2de455c
- [Attention] MLA - Flashinfer Ragged Prefill (#20034) · 5b032352
  Alexander Matveev authored Jul 10, 2025
  
  5b032352
- [Model] Support HF format of minimax (#20211) · 922f3164
  Michael Goin authored Jul 11, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  922f3164
- [fix]: disable cutlass block scaled group gemm for EP (#20781) · 5923ab95
  Duncan Moss authored Jul 10, 2025
```
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
```
  5923ab95
- Add kimi-k2 tool parser (#20789) · 0cf893ca
  bigmoyan authored Jul 11, 2025
```
Signed-off-by: wangzhengtao <wangzhengtao@moonshot.cn>
Co-authored-by: wangzhengtao <wangzhengtao@moonshot.cn>
Co-authored-by: wangzhengtao <wangzhengtao@msh.team>
```
  0cf893ca
10 Jul, 2025 20 commits
- [Docs] Lazy import gguf (#20785) · b854321f
  Simon Mo authored Jul 10, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  b854321f
- [Misc] MoE ModularKernel : Introduce TopKWeightAndReduce (#20648) · f0c98cae
  Varun Sundar Rabindranath authored Jul 10, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  f0c98cae
- [KVConnector] Always call connector `clear_metadata()` at end of step (#20756) · 574ad60d
  Nick Hill authored Jul 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: David Ben-David <sdavidbd@gmail.com>
```
  574ad60d
- [Bugfix] Fused MoE Modular Kernel chunking loop (#20392) · fdadb6f4
  Varun Sundar Rabindranath authored Jul 10, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  fdadb6f4
- [Core] Add Support for Default Modality Specific LoRAs [generate / chat completions] (#19126) · 41060c6e
  Alex Brooks authored Jul 10, 2025
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  41060c6e
- [Bugfix] Remove assertion of expert_map being None (#20714) · 3de2ed76
  Ming Yang authored Jul 10, 2025
```
Signed-off-by: Ming Yang <yming@meta.com>
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  3de2ed76
- [CI] Fix pre commit issue (#20782) · 299252ea
  Wentao Ye authored Jul 10, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  299252ea
- [V0][V1][Core] Add outlines integration for V1, and update V0 integration. (#15975) · d6902ce7
  Nathan Hoos authored Jul 10, 2025
```
Signed-off-by: Nathan Hoos <thwackyy.y@gmail.com>
```
  d6902ce7
- [Bugfix] [CI] Fix Tensorizer LoRA test (#20760) · 5e53c89a
  Sanger Steel authored Jul 10, 2025
```
Signed-off-by: Sanger Steel <sangersteel@gmail.com>
```
  5e53c89a
- [Model][VLM] Support JinaVL Reranker (#20260) · 4bed1677
  shineran96 authored Jul 11, 2025
```
Signed-off-by: shineran96 <shinewang96@gmail.com>
```
  4bed1677
- [Model] Add reason parser for Hunyuan A13B Model. (#20625) · b140416a
  Asher authored Jul 11, 2025
```
Signed-off-by: Asher Zhang <asherszhang@tencent.com>
```
  b140416a
- [ROCm][Regression] Remove tensor creation that harms performance on ROCm (#20741) · 5b8366b6
  Gregory Shtrasberg authored Jul 10, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  5b8366b6
- [Doc] Add engine args back in to the docs (#20674) · 3482fd7e
  Harry Mellor authored Jul 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  3482fd7e
- [KVConnector] Aggregate finished requests on the scheduler (#19555) · cc876d0f
  Or Ozeri authored Jul 10, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  cc876d0f
- [TPU][Core]Make load weight exceed hbm error more instructive for customers (#20644) · fdfd409f
  Chenyaaang authored Jul 10, 2025
```
Signed-off-by: Chenyaaang <chenyangli@google.com>
```
  fdfd409f
- [BugFix] Fix `VllmConfig()` construction on all platforms (#20695) · ffbcc9e7
  Nick Hill authored Jul 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  ffbcc9e7
- [BugFix][CPU] Fix CPU worker dependency on cumem_allocator (#20696) · 59389c92
  Nick Hill authored Jul 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  59389c92
- [Frontend] Support Tool Calling with both `tool_choice='required'` and `$defs`. (#20629) · 8f2720de
  Chauncey authored Jul 10, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  8f2720de
- Correct PPMissingLayer handling in Deepseek-V2-Lite PP deployment (#20665) · ad6c2e1a
  Seiji Eicher authored Jul 09, 2025
```
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
```
  ad6c2e1a
- [Misc] DP : Add ExpertTokensMetadata (#20332) · 805d62ca
  Varun Sundar Rabindranath authored Jul 09, 2025
```
Signed-off-by: Varun <vsundarr@redhat.com>
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun <vsundarr@redhat.com>
```
  805d62ca
09 Jul, 2025 15 commits
- [Misc] Simplify the prefix caching logic on draft tokens (#20701) · 7c12a765
  Woosuk Kwon authored Jul 09, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  7c12a765
- [BugFix]: Properly set engine_id when using multi connector (#19487) · cd587c93
  Yiming authored Jul 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: leiyiming <leiyiming@kingsoft.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  cd587c93
- [Feature][Quantization] MXFP4 support for MOE models (#17888) · 332d4cb1
  fxmarty-amd authored Jul 09, 2025
```
Signed-off-by: Felix Marty <felmarty@amd.com>
Signed-off-by: Bowen Bao <bowenbao@amd.com>
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Bowen Bao <bowenbao@amd.com>
```
  332d4cb1
- [Kernel] Add Conch backend for mixed-precision linear layer (#19818) · bf03ff35
  Jacob Manning authored Jul 09, 2025
```
Signed-off-by: Jacob Manning <jmanning+oss@stackav.com>
```
  bf03ff35
- [Kernel] Triton implementation of causal-conv1d for Mamba-based models (#18218) · 47043eb6
  Tuan, Hoang-Trong authored Jul 09, 2025
```
Signed-off-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  47043eb6
- Support Llama 4 for cutlass_moe_fp4 (#20453) · 31b96d1c
  Michael Goin authored Jul 10, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  31b96d1c
- [XPU][CI] enhance xpu test support (#20652) · a3e4e85e
  Liangliang Ma authored Jul 10, 2025
```
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
Co-authored-by: zhenwei-intel <zhenweiliu@habana.ai>
```
  a3e4e85e
- [Bugfix] Fix handling of Tensorizer arguments for LoadConfig (#20643) · 4ac9c33f
  Sanger Steel authored Jul 09, 2025
```
Signed-off-by: Sanger Steel <sangersteel@gmail.com>
```
  4ac9c33f
- [Benchmark] Parameterization of streaming loading of multimodal datasets (#20528) · 9ff2af6d
  Li Wang authored Jul 09, 2025
```
Signed-off-by: wangli <wangli858794774@gmail.com>
```
  9ff2af6d
- [Bugfix] Fix the issue where `reasoning_content` is `None` when Thinkng is... · 2155e95e
  Chauncey authored Jul 09, 2025
```
[Bugfix] Fix the issue where `reasoning_content` is `None` when Thinkng is enabled and `tool_choice` is set to `'required'`. (#20662)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  2155e95e
- [Intel GPU] support ray as distributed executor backend for XPU. (#20659) · b6e7e3d5
  Kunshang Ji authored Jul 09, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  b6e7e3d5
- [XPU] Use spawn with XPU multiprocessing (#20649) · e760fcef
  Dmitry Rogozhkin authored Jul 09, 2025
```
Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
```
  e760fcef
- [Misc] Fix the size of batched_dummy_mm_inputs in profile_run (#20434) · 6bbf1795
  B-201 authored Jul 09, 2025
```
Signed-off-by: bk-201 <joy25810@foxmail.com>
```
  6bbf1795
- [feat] enable SM100 CUTLASS block scaled group gemm for smaller batch sizes (#20640) · 97abeb1d
  Duncan Moss authored Jul 08, 2025
```
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
```
  97abeb1d
- [Bugfix] set default set cuda_graph_sizes to min(self.max_num_seqs * 2, 512) (#20628) · 34dad19e
  zhrrr authored Jul 09, 2025
```
Signed-off-by: izhuhaoran <izhuhaoran@qq.com>
```
  34dad19e