Commits · 90b139cfffd52ee2563260a89409fee60f7329f2 · OpenDAS / vllm_cscc

25 Sep, 2025 3 commits

Enable Fbgemm NVFP4 on Dense models (#25609) · 90b139cf
Saman A. Pour authored Sep 24, 2025
```
Signed-off-by: Saman Keon <samanamp@outlook.com>
```
90b139cf

[Bug] Dynamo Unsupported due to `BasevLLMParameter.torch_function` calling... · 4492e3a5

Wentao Ye authored Sep 24, 2025


[Bug] Dynamo Unsupported due to `BasevLLMParameter.torch_function` calling disabled super() (#25613)
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>

4492e3a5

[Kernel] Support DCP for Triton backend (#25132) · 05c19485
Wei Wei authored Sep 24, 2025
```
Signed-off-by: Wei Wei <wwei6@meta.com>
```
05c19485

24 Sep, 2025 16 commits
- [Model] Improve DotsOCRForCausalLM (#25466) · 52d0cb84
  Jee Jee Li authored Sep 25, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  52d0cb84
- [Refactor] Use DeepGEMM Col Major TMA Aligned Tensor (#25517) · 1f291412
  Wentao Ye authored Sep 24, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  1f291412
- feat: BF16 FlashInfer Fused Cutlass MOE for Hopper and Blackwell Expert Parallel (#25503) · 6160ba41
  Duncan Moss authored Sep 24, 2025
```
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
```
  6160ba41
- [Docs] Enable `fail_on_warning` for the docs build in CI (#25580) · 8c853050
  Harry Mellor authored Sep 24, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8c853050
- Support mnnvl all2allv from Flashinfer (#21003) · 54e42b72
  Shu Wang authored Sep 24, 2025
```
Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
  54e42b72
- [Misc] Improve type annotations for jsontree (#25577) · 9313be50
  Cyrus Leung authored Sep 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9313be50
- [V0 Deprecation] Remove max_seq_len_to_capture (#25543) · 2e19a848
  Woosuk Kwon authored Sep 24, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2e19a848
- [Misc]] Move processing context to multimodal directory (#25548) · 6488f348
  Cyrus Leung authored Sep 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  6488f348
- [CI/Build] Fix v1 OOT registration test (#25547) · 27ec3c78
  Isotr0py authored Sep 24, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  27ec3c78
- [Bugfix][CPU] Skip unsupported custom op register on CPU (#25534) · 1cbcfb94
  Li, Jiang authored Sep 24, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  1cbcfb94
- [Perf] Fix jit compiles at runtime of fla gated delta rule (#25432) · d747c2ef
  Corey Lowman authored Sep 23, 2025
```
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  d747c2ef
- [KV sharing] Re-land Gemma3n model changes from #22628 (#24357) · 77d90699
  Yong Hoon Shin authored Sep 23, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  77d90699
- [fix]: add Arm 4bit fused moe support (#23809) · 359d2930
  Nikhil Gupta authored Sep 24, 2025
```
Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>
```
  359d2930
- [Core] Support weight_loader_v2 for `UnquantizedLinearMethod` (#23036) · de94289a
  Kyle Sayers authored Sep 24, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  de94289a
- [Bug] Fix AttributeError: 'FusedMoE' object has no attribute... · 88d7bdbd
  Wentao Ye authored Sep 23, 2025
```
[Bug] Fix AttributeError: 'FusedMoE' object has no attribute 'w13_weight_scale'. Did you mean: 'w13_weight_scale_inv' (#25519)
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>
```
  88d7bdbd
- Add CUTLASS FP8 MOE benchmark scripts and kernel config (#25302) · 0d235b87
  Chenxi Yang authored Sep 23, 2025
```
Signed-off-by: Chenxi Yang <cxyang@fb.com>
Co-authored-by: Chenxi Yang <cxyang@fb.com>
```
  0d235b87
23 Sep, 2025 19 commits

[ROCm] Small functional changes for gptoss (#25201) · bde2a1a8
Juan Villamizar authored Sep 23, 2025
```
Signed-off-by: jpvillam <jpvillam@amd.com>
Co-authored-by: jpvillam <jpvillam@amd.com>
```
bde2a1a8

[Kernel] [Mamba] Remove BLOCK_H=1 from list of tuneable configurations for... · 5e25b122

Thomas Parnell authored Sep 24, 2025


[Kernel] [Mamba] Remove BLOCK_H=1 from list of tuneable configurations for `_chunk_cumsum_fwd_kernel` (#25197)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Chih-Chieh-Yang <chih.chieh.yang@ibm.com>

5e25b122

Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512) · 7361ab37
Michael Goin authored Sep 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
7361ab37
[CI/Build] Fix and re-enable v1 PP test on CI (#25496) · ae002924
Isotr0py authored Sep 24, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
ae002924
[Bugfix] Fix for the import error from #24588 (#25481) · 690f948e
Gregory Shtrasberg authored Sep 23, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
690f948e
[Bugfix] Lower gpt-oss max cudagraph size to 992 to be compatible with FA3 (#25508) · a8ffc4f0
Michael Goin authored Sep 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
a8ffc4f0
[Speculators][Speculative Decoding] Fix gpt-oss eagle3 accuracy issue (#25406) · d5944d51
jiahanc authored Sep 23, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
```
d5944d51

[Performance] Move apply_w8a8_block_fp8_linear to an op class (#24666) · 63400259

ElizaWszola authored Sep 23, 2025


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: ElizaWszola <elizaw.9289@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

63400259

[ROCm] Add skinny gemm bias support for dtypes fp16,bf16,fp8 (#24988) · a3a78280

Hashem Hashemi authored Sep 23, 2025


Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
Signed-off-by: Hashem Hashemi <159079214+amd-hhashemi@users.noreply.github.com>

a3a78280

[Kernels] Support blocked fp8 quantization for compressed tensors MoE (#25219) · f11e3c51
bnellnm authored Sep 23, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
f11e3c51

[Core/DBO][2/N] Dual-Batch Overlap add DeepEP High Throughput support and Prefill support (#24845) · cc1dc7ed

Lucas Wilkinson authored Sep 23, 2025


Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

cc1dc7ed

[V1] Remove V0 code paths for Hybrid models (#25400) · a903669e
Thomas Parnell authored Sep 23, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
a903669e

[BugFix] Register expert_map as named buffer for wake_up and sleep (#25458) · 61d1b355

Joel authored Sep 23, 2025


Signed-off-by: wuxibin <wuxibin@bytedance.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

61d1b355

[Bugfix] Fix idefics3 `tie_word_embeddings` (#25454) · 231c2c63
Isotr0py authored Sep 23, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
231c2c63
[Misc] Move DP for ViT code inside model executor dir (#25459) · babad6e5
Cyrus Leung authored Sep 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
babad6e5
Handle triton kernel import exception (#25319) · ba8d2165
Ming Yang authored Sep 23, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
ba8d2165
[Model] Enable DP for ViT in Qwen2-VL (#25445) · c98be0a2
Cyrus Leung authored Sep 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
c98be0a2
[DP/EP][GPTOSS] Use triton matmul-ogs kernels for GPTOSS DP/EP (#24588) · e8db44f8
Varun Sundar Rabindranath authored Sep 23, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
e8db44f8

[feat] Support MRoPE + YaRN (#25384) · fc97733d

JJJYmmm authored Sep 23, 2025


Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com>
Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com>

fc97733d

22 Sep, 2025 2 commits

[EPLB] Reduce EPLB Inference Overhead (#24573) · 06a41334

Bowen Wang authored Sep 22, 2025

Signed-off-by: Bowen Wang <abmfy@icloud.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

06a41334

[Kernel] MI-300X triton moe configs (#23445) · ac243886
Sara-KS authored Sep 22, 2025
```
Signed-off-by: Sara Kokkila Schumacher <saraks@ibm.com>
```
ac243886