Commits · 6e672daf62e7b03ff1dcf74e4206dad07d39d4ec · OpenDAS / vllm_cscc

31 Jul, 2025 2 commits
- [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
25 Jul, 2025 6 commits
- [Model] Replace Mamba2 RMSNorm Gated with Fused Triton Kernel (#20839) · eab2f398
  Chih-Chieh Yang authored Jul 25, 2025
```
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
Signed-off-by: Yu Chin Fabian Lim <fabian.lim@gmail.com>
Signed-off-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com>
Co-authored-by: Yu Chin Fabian Lim <fabian.lim@gmail.com>
```
  eab2f398
- [V1] Get supported tasks from model runner instead of model config (#21585) · 46d81d69
  Cyrus Leung authored Jul 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  46d81d69
- Add H20-3e fused MoE kernel tuning configs for Qwen3-Coder-480B-A35B-Instruct (#21598) · 8ed01e32
  Xu Wenqing authored Jul 25, 2025
```
Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
```
  8ed01e32
- [Bugfix] DeepGemm utils : Fix hardcoded type-cast (#21517) · 2212cd6c
  Varun Sundar Rabindranath authored Jul 25, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  2212cd6c
- [Kernel] adding fused_moe configs for upcoming granite4 (#21332) · ce3a9b13
  Burkhard Ringlein authored Jul 25, 2025
```
Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  ce3a9b13
- [Bug] Fix DeepGemm Init Error (#21554) · 633f6e80
  Wentao Ye authored Jul 24, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  633f6e80
24 Jul, 2025 4 commits
- [MoE] More balanced expert sharding (#21497) · fe56180c
  Woosuk Kwon authored Jul 24, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
  fe56180c
- Update flashinfer CUTLASS MoE Kernel (#21408) · 1b25f1fe
  Shu Wang authored Jul 24, 2025
```
Signed-off-by: Shu Wang. <shuw@nvidia.com>
```
  1b25f1fe
- [Misc] Fix duplicate FusedMoEConfig debug messages (#21455) · f0f4de8f
  Nick Hill authored Jul 24, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  f0f4de8f
- [TPU][Bugfix] fix moe layer (#21340) · e74bfc70
  Chengji Yao authored Jul 24, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  e74bfc70
23 Jul, 2025 1 commit
- [Cleanup] Only log MoE DP setup warning if DP is enabled (#21315) · f002e9a8
  Michael Goin authored Jul 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f002e9a8
22 Jul, 2025 5 commits
- [Perf] Cuda Kernel for Per Token Group Quant (#21083) · 774d0c01
  Wentao Ye authored Jul 22, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  774d0c01
- [feat]: add SM100 support for cutlass FP8 groupGEMM (#20447) · 2c8db17c
  Duncan Moss authored Jul 22, 2025
```
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  2c8db17c
- [perf] Add fused MLA QKV + strided layernorm (#21116) · 4fb56914
  Mickaël Seznec authored Jul 22, 2025
```
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  4fb56914
- Update fp4 quantize API (#21327) · 9e23ad96
  Shu Wang authored Jul 22, 2025
```
Signed-off-by: Shu Wang <shuw@nvidia.com>
```
  9e23ad96
- Revert "[Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) (#21334) · e7b20426
  Ming Yang authored Jul 21, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  e7b20426
21 Jul, 2025 3 commits
- [perf] Speed up align sum kernels (#21079) · 0ec82edd
  Himanshu Jaju authored Jul 21, 2025
```
Signed-off-by: Himanshu Jaju <hj@mistral.ai>
```
  0ec82edd
- Add Nvidia ModelOpt config adaptation (#19815) · 6b46c4b6
  Zhiyu authored Jul 21, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
```
  6b46c4b6
- [Model][1/N] Support multiple poolers at model level (#21227) · 042af0c8
  Cyrus Leung authored Jul 21, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  042af0c8
19 Jul, 2025 4 commits
- [V1] [Hybrid] Enable piecewise CUDA Graph for mamba layers (#21194) · 881e3cbe
  Thomas Parnell authored Jul 19, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  881e3cbe
- [NVIDIA] Add SM100 Flashinfer MoE blockscale fp8 backend for low latency (#20645) · 6d0734c5
  Kaixi Hou authored Jul 19, 2025
```
Signed-off-by: kaixih <kaixih@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  6d0734c5
- [Kernel][Performance] Tweak MoE Batched silu_mul_fp8_quant_deep_gemm kernel (#21193) · dcc6cfb9
  Varun Sundar Rabindranath authored Jul 19, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  dcc6cfb9
- [V0 Deprecation] Remove V0 Spec Decode workers (#21152) · dd572c0a
  Woosuk Kwon authored Jul 18, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  dd572c0a