Commits · c488b928a736109cc0a0c824340b928a4f118b2f · OpenDAS / vllm_cscc · GitLab

13 Jul, 2025 6 commits
- [V1] [ROCm] [AITER] Upgrade AITER to commit `916bf3c` and bugfix APIs (#20880) · 80d38b8a
  TJian authored Jul 13, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  80d38b8a
- Support for LlamaForSequenceClassification (#20807) · bd4c1e6f
  Minkyu Kim authored Jul 13, 2025
```
Signed-off-by: thechaos16 <thechaos16@gmail.com>
```
  bd4c1e6f
- [Core] Support multiple tasks per model (#20771) · 020f58ab
  Nicolò Lucchesi authored Jul 13, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  020f58ab
- [Refactor] Change the way of import triton (#20774) · c1acd6d7
  Wentao Ye authored Jul 12, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c1acd6d7
- [Bugfix] Fix a couple PPLX+CUTLASS MoE bugs (#20825) · 3b3b778d
  ElizaWszola authored Jul 13, 2025
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
```
  3b3b778d
- [Perf] Use Triton instead of Torch for DeepGEMM Per Token Group Quant (#20841) · 42d440c2
  Wentao Ye authored Jul 12, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  42d440c2
12 Jul, 2025 11 commits
- [Bugfix] Restrict Machete to only run on Hopper (#20830) · 6e2c176e
  Michael Goin authored Jul 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  6e2c176e
- [Bugfix] Fix Tensor Parallelism Padding Consistency in Granite Models (#20843) · c2a2f19a
  Alex Brooks authored Jul 12, 2025
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  c2a2f19a
- [Model] New model support for microsoft/Phi-4-mini-flash-reasoning (#20702) · 2c11a738
  Congcong Chen authored Jul 12, 2025
```
Signed-off-by: Congcong Chen <congcongchen@microsoft.com>
```
  2c11a738
- Enable ModelOpt Llama4 fp8 checkpoint deployment (#20419) · 4afe687a
  Zhiyu authored Jul 11, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
```
  4afe687a
- [Bug] Fix DeepGemm for EP low latency case (#20833) · 0d4891cd
  Wentao Ye authored Jul 12, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  0d4891cd
- [Frontend] Abstract prompt and SpeechToTextConfig for transcriptions models (#20637) · 3c7d942d
  Nicolò Lucchesi authored Jul 12, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  3c7d942d
- [Bugfix] : Fix typo - logger.warn_once -> logger.warning_once (#20852) · 890323dc
  Varun Sundar Rabindranath authored Jul 12, 2025
  
  890323dc
- [CI/Build] Ensure compatability with Transformers v4.53 (#20541) · 01cae377
  Isotr0py authored Jul 12, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  01cae377
- [Bugfix] Fix tensor parallel issue in Qwen3 reranker weight loading (#20682) · 11c01986
  yurhett authored Jul 12, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  11c01986
- [Bugfix] Lazy import fused_experts in BitsAndBytesMoEMethod to avoid break... · b1235c3e
  Li, Jiang authored Jul 12, 2025
```
[Bugfix] Lazy import fused_experts in BitsAndBytesMoEMethod to avoid break not-cuda-alike devices  (#20822)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  b1235c3e
- [Misc] Restrict deep_gemm's log output (#20827) · 44d02f54
  Jee Jee Li authored Jul 12, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  44d02f54
11 Jul, 2025 7 commits
- [Misc] Add unit tests for MoE ModularKernel combinations + Profiling utility (#20449) · 53fa4573
  Varun Sundar Rabindranath authored Jul 11, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  53fa4573
- [Quantization][1/N] MoE support BNB-Inflight Quantization (#20061) · 8020e98c
  Jee Jee Li authored Jul 11, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  8020e98c
- [V1] Enable Mamba2 layers other than MambaMixer2 in the v1 engine (#20660) · 5d09152f
  nopperl authored Jul 11, 2025
```
Signed-off-by: nopperl <54780682+nopperl@users.noreply.github.com>
```
  5d09152f
- [Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf (#19830) · 31d5c179
  Luka Govedič authored Jul 11, 2025
```
Signed-off-by: Luka Govedic <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  31d5c179
- [Feature] Integrate SM100 DeepGEMM support (#20087) · e2de455c
  Wentao Ye authored Jul 10, 2025
  
  e2de455c
- [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
10 Jul, 2025 10 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
- [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
- [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
- [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
- [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
- 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 6 commits
- [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
- [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
- [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