Commits · d57dc2364e88e9a1a3e8dc3f6ff8486a7ba040dd · OpenDAS / vllm_cscc

07 Aug, 2025 7 commits

[Misc] Enhance code formatting in mxfp4.py (#22423) · 136825de
Woosuk Kwon authored Aug 07, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
136825de

Add H20-3e fused MoE kernel tuning configs for GLM-4.5 (#22433) · c2dba2db

JaceyShao authored Aug 07, 2025


Signed-off-by: shaojunqi <shaojunqi.sjq@alibaba-inc.com>
Co-authored-by: shaojunqi <shaojunqi.sjq@alibaba-inc.com>

c2dba2db

[Misc] Support routing logic simulation (#21990) · 82216dc2

Ming Yang authored Aug 06, 2025

Signed-off-by: Ming Yang <minos.future@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

82216dc2

[Bugfix] EPLB load statistics problem (#22167) · 4be02a37

WeiQing Chen authored Aug 07, 2025


Signed-off-by: ycyaw66 <497410282@qq.com>
Signed-off-by: David Chen <530634352@qq.com>
Co-authored-by: ycyaw66 <497410282@qq.com>

4be02a37

[Bugfix] Add proper comparison for package versions (#22314) · 609b533c
Syed Muhammad Bin Asif authored Aug 07, 2025
```
Signed-off-by: Syed Muhammad Bin Asif <syedmba7@connect.hku.hk>
```
609b533c
[Bug] Fix B200 DeepGEMM E8M0 Accuracy Issue (#22399) · eec890c1
Wentao Ye authored Aug 06, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
eec890c1
[v1] - Mamba1 Attention Metadata (#21249) · 46a13949
Asaf Joseph Gardin authored Aug 07, 2025
```
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
```
46a13949

06 Aug, 2025 2 commits

[gpt-oss] flashinfer mxfp4 (#22339) · 31f09c61

Yongye Zhu authored Aug 06, 2025


Signed-off-by: simon-mo <xmo@berkeley.edu>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>

31f09c61

[Bugfix] Fix MoE BNB version (#22260) · 8e6c7e87
Jee Jee Li authored Aug 06, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
8e6c7e87

05 Aug, 2025 4 commits
- [Model] Pooling model activation supports per request control by PoolingParams (#20538) · 586f2867
  wang.yuqi authored Aug 05, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  586f2867
- [Log] DeepGEMM Update Log for Unaligned Problem Size (#22208) · d7b28f34
  Wentao Ye authored Aug 04, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  d7b28f34
- [FEAT] Refactor ROPE into module (#22192) · 6ad6b8e1
  TJian authored Aug 04, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  6ad6b8e1
- [NVIDIA] Auto detect modelopt quant and fix DSR1-FP4 weight loading (#22073) · bdcb42e4
  Po-Han Huang (NVIDIA) authored Aug 05, 2025
  
  bdcb42e4
04 Aug, 2025 1 commit
- [feat] move WEIGHT_SCALE_SUPPORTED into raise block to accelerate RLHF weight loading (#21164) · c1b4eb04
  Weixiao Huang authored Aug 04, 2025
```
Signed-off-by: huangweixiao <huangweixiao@msh.team>
```
  c1b4eb04
03 Aug, 2025 1 commit

[CI/Build][Bugfix] Fix Qwen2.5 tests in CPU CI via fallback silu_and_mul to... · b5dfb94f

Li, Jiang authored Aug 03, 2025


[CI/Build][Bugfix] Fix Qwen2.5 tests in CPU CI via fallback silu_and_mul to torch native implementation (#22145)
Signed-off-by: jiang1.li <jiang1.li@intel.com>

b5dfb94f

02 Aug, 2025 6 commits
- [xpu]support moe models on XPU platform (#21643) · 73e1b9b1
  Yan Ma authored Aug 02, 2025
```
Signed-off-by: yan <yan.ma@intel.com>
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  73e1b9b1
- [Model] Mamba2 preallocate SSM output tensor to avoid d2d copy overhead (#21075) · b690e348
  Chih-Chieh Yang authored Aug 02, 2025
```
Signed-off-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com>
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
```
  b690e348
- for glm-4.1V update (#22000) · 25373b6c
  Yuxuan Zhang authored Aug 02, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  25373b6c
- [Bugfix] Mamba2 remove bugged initial state condition in chunk scan (#22034) · c64861d6
  Chih-Chieh Yang authored Aug 02, 2025
```
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
```
  c64861d6
- [Misc] DeepGemmExperts : Avoid JIT generation in the hot-path (#21955) · a65f46be
  Varun Sundar Rabindranath authored Aug 02, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  a65f46be
- feat: Add Support GPTQ Quantization MOE on ROCM vllm serve (#21733) · 3654847d
  JartX authored Aug 02, 2025
  
  3654847d
01 Aug, 2025 1 commit
- [Bugfix] [Performance] DeepEPHighThroughput + DeepSeek : Quant before Dispatch (#21837) · ac45c44d
  Varun Sundar Rabindranath authored Aug 01, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  ac45c44d
31 Jul, 2025 3 commits
- [Feature] Add Flashinfer MoE Support for Compressed Tensor NVFP4 (#21639) · c3e0e933
  Wentao Ye authored Jul 31, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c3e0e933
- [NVIDIA] Add SM100 Flashinfer MoE per tensor scale fp8 backend (#21458) · 207b750e
  amirkl94 authored Jul 31, 2025
```
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  207b750e
- [Misc] Expand SUPPORTED_HIDDEN_SIZES for DeepEP low-latency kernels (#21818) · 0f7919fc
  Jee Jee Li authored Jul 31, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  0f7919fc
30 Jul, 2025 1 commit
- [NVIDIA] Fix Llama4 Scout FP4 functionality issues (#21499) · ff08e519
  Po-Han Huang (NVIDIA) authored Jul 30, 2025
```
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
```
  ff08e519
29 Jul, 2025 3 commits

[Bugfix]fix mixed bits and visual language model quantization in AutoRound (#21802) · ad341c51
Wenhua Cheng authored Jul 29, 2025
```
Signed-off-by: Wenhua Cheng <wenhua.cheng@intel.com>
```
ad341c51

[Model]: Fused MoE for nomic-embed-text-v2-moe (#18321) · a4528f0c

Isotr0py authored Jul 29, 2025


Signed-off-by: isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

a4528f0c

[Refactor] Merge Compressed Tensor FP8 `CompressedTensorsW8A8Fp8MoEMethod` and... · 48b763d6

Wentao Ye authored Jul 28, 2025


[Refactor] Merge Compressed Tensor FP8 `CompressedTensorsW8A8Fp8MoEMethod` and `CompressedTensorsW8A8Fp8MoECutlassMethod` (#21775)
Signed-off-by: yewentao256 <zhyanwentao@126.com>

48b763d6

28 Jul, 2025 5 commits
- [Feat]: Add support for Dynamic Quant 4 bit CPU kleidiai kernels (#17112) · 89ac266b
  Nikhil Gupta authored Jul 28, 2025
```
Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  89ac266b
- [AMD][BugFix] Fix omission of wvSplitK kernel for small batch sizes (1-4) due... · b361f14e
  rasmith authored Jul 28, 2025
```
[AMD][BugFix] Fix omission  of wvSplitK kernel for small batch sizes (1-4) due to torch.compile (#21350)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
```
  b361f14e
- [v1][mamba] Added mamba_type into MambaSpec (#21715) · a6c05028
  Asaf Joseph Gardin authored Jul 28, 2025
```
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
```
  a6c05028
- [FEAT] [ROCm] [AITER]: Add AITER HIP block quant kernel (#21242) · e626d286
  TJian authored Jul 27, 2025
  
  e626d286
- [Misc] Add fused_moe configs for Qwen3-Coder-480B-A35B-Instruct-FP8 (#21700) · 04ff4be3
  Jee Jee Li authored Jul 28, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  04ff4be3
27 Jul, 2025 2 commits
- Fix CUDA permute/unpermute for use with DeepGemm Moe (#17934) · 57c22e57
  Caleb_Du authored Jul 27, 2025
```
Signed-off-by: Caleb_Du <Caleb_Du@zju.edu.cn>
```
  57c22e57
- [Refactor] Refactor MOE NVFP4 Code Base: ModelOpt + Compressed Tensor (#21631) · bda9d053
  Wentao Ye authored Jul 27, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  bda9d053
26 Jul, 2025 4 commits
- [NVIDIA] Explicitly disable shuffled weights for flashinfer blockscale moe fp8 kernels (#21411) · de509ae8
  Kaixi Hou authored Jul 26, 2025
```
Signed-off-by: kaixih <kaixih@nvidia.com>
```
  de509ae8
- [Refactor] Remove `moe_align_block_size_triton` (#21335) · 56e544f2
  Wentao Ye authored Jul 26, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  56e544f2
- [Feature] Add support for MoE models in the calibration-free RTN-based quantization (#20766) · 7ae75fa6
  Alex Kogan authored Jul 25, 2025
```
Signed-off-by: Alex Kogan <alex.kogan@oracle.com>
```
  7ae75fa6
- [Perf] Cuda Kernel for Int8 Per Token Group Quant (#21476) · 75d29cf4
  Wentao Ye authored Jul 25, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  75d29cf4