Commits · a00d88973daf9a151ecbd4c740ca99645715b9df · OpenDAS / vllm_cscc

11 Dec, 2025 5 commits
- [EPLB] Support EPLB w/ NVFP4 (#29804) · a00d8897
  Andrew Briand authored Dec 11, 2025
```
Signed-off-by: Andrew Briand <abriand@nvidia.com>
Co-authored-by: Andrew Briand <abriand@nvidia.com>
```
  a00d8897
- [Perf] Optimize deepgemm experts initialization, 3.9% TTFT improvement (#30494) · c817b141
  Wentao Ye authored Dec 11, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: li-jinpeng <3332126450@qq.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  c817b141
- Standardise `get_rope` to use `rope_parameters["partial_rotary_factor"]`, not `rotary_dim` (#30389) · cf3eacfe
  Harry Mellor authored Dec 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  cf3eacfe
- [Feature] AWQ marlin quantization support for fused moe with lora (#30442) · 0e71eaa6
  汪志鹏 authored Dec 12, 2025
```
Signed-off-by: princepride <wangzhipeng628@gmail.com>
```
  0e71eaa6
- [Bugfix] Fix grouped_topk pytorch impl when num_experts can't be grouped properly (#29439) · d1e1fb43
  Divakar Verma authored Dec 10, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  d1e1fb43
10 Dec, 2025 2 commits
- Fix typos in comments across multiple files (#30345) · 3bdd4266
  Wilson Wu authored Dec 10, 2025
```
Signed-off-by: Wilson Wu <iwilsonwu@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  3bdd4266
- [Bugfix] Fix fp8 DeepGemm compilation issues (#30336) · 2e7035dd
  ElizaWszola authored Dec 10, 2025
  
  2e7035dd
09 Dec, 2025 12 commits

[Rocm][torch.compile] Adding layernorm + fp8 block quant and silu + fp8 block... · 3c680f4a

Charlie Fu authored Dec 09, 2025


[Rocm][torch.compile] Adding layernorm + fp8 block quant and silu + fp8 block quant for Aiter (#25693)
Signed-off-by: charlifu <charlifu@amd.com>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Charlie Fu <Charlie.Fu@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: wuhuikx <hattie.wu@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>

3c680f4a

[Quantization] FP8 Weight Reloading for Quantized RL Rollout (#28480) · fccd5325
Kyle Sayers authored Dec 09, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
fccd5325

[MoE][Refactor] Remove most arguments to FusedMoEMethodBase.apply (#29066) · 00e5cbb9

bnellnm authored Dec 09, 2025

Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>

00e5cbb9

[Feature] Batch-Invariant Support for FA2 and LoRA (#30018) · 5dcd593b

liuquan authored Dec 09, 2025


Signed-off-by: quanliu <18646313696@163.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

5dcd593b

[ROCm] Aiter Quant Kernels (#25552) · ee14644b
vllmellm authored Dec 09, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
ee14644b
[Bugfix]: Fix glm46 awq marlin moe wna16 compatibility (#30210) · 1166c31c
Dongjie Zou authored Dec 09, 2025
```
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
```
1166c31c

[Model][Quantization] Restore MoE + GGUF models support (incl. Qwen3 MoE) by... · 58d5b3f5

Tsukasa OI authored Dec 09, 2025


[Model][Quantization] Restore MoE + GGUF models support (incl. Qwen3 MoE) by allowing Sideload Parameters (#30116)
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

58d5b3f5

[Bugfix] Fix compressed-tensors models failing to load with transformers backend (#30287) · 03b91f72

Michael Goin authored Dec 08, 2025

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

03b91f72

[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691) · f6227c22
czhu-cohere authored Dec 08, 2025
```
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
```
f6227c22

[Bugfix] Fix DeepGEMM after #29546 (#30267) · ae339b1a

Zhewen Li authored Dec 08, 2025


Signed-off-by: zhewenli <zhewenli@meta.com>
Signed-off-by: Zhewen Li <zhewenli@meta.com>

ae339b1a

[Feature] Batch invariant: Enable `TRITON_MLA` without prefix-caching (#29125) · d9417096
Wentao Ye authored Dec 08, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
d9417096
[moe] Allow disabling DP chunking (#29936) · 9d6235ca
Ming Yang authored Dec 08, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
9d6235ca

08 Dec, 2025 3 commits
- Add SpecDec support to `selective_state_update` (#29488) · ae0f69b1
  roikoren755 authored Dec 08, 2025
```
Signed-off-by: Roi Koren <roik@nvidia.com>
```
  ae0f69b1
- online fp8 quant with streaming weight post-processing (#29196) · 0d402d26
  Vasiliy Kuznetsov authored Dec 08, 2025
```
Signed-off-by: vasiliy <vasiliy@fb.com>
```
  0d402d26
- [ROCm] [Fused Moe EP] Use binary expert mask for aiter fused moe kernel (#29773) · c6df05eb
  Zhiwei authored Dec 08, 2025
```
Signed-off-by: ZhiweiYan-96 <zhiwei.yan@amd.com>
```
  c6df05eb
07 Dec, 2025 3 commits

[Performance] Fused blockwise quant RMS norm (#27883) · af0444bf

ElizaWszola authored Dec 07, 2025


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>

af0444bf

[Perf] Deepgemm fused layout kernel for activations, 4.3% throughput... · 541a2ef8

Wentao Ye authored Dec 07, 2025


[Perf] Deepgemm fused layout kernel for activations, 4.3% throughput improvement, 10.7% TTFT improvement. (#29546)
Signed-off-by: yewentao256 <zhyanwentao@126.com>

541a2ef8

[Kernel][MoE] optimize `moe_align_block_size` (#29642) · 879ddb09

Jinzhen Lin authored Dec 07, 2025


Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

879ddb09

06 Dec, 2025 3 commits
- fix#30092 Kimi-Linear model loading failure with missing indexer_rotary_emb (#30093) · e3fbb6f1
  Dongjie Zou authored Dec 05, 2025
```
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
```
  e3fbb6f1
- Fix AWQ MoE marlin check issue in marlin_utils.py for AMD backend (#30102) · c4d62618
  yuttian1 authored Dec 06, 2025
```
Signed-off-by: yuttian1 <yuttian@amd.com>
```
  c4d62618
- [CI/Build][AMD][Quantization] Fix test_int8_kernel.py by updating int8_utils... · dc839ad0
  rasmith authored Dec 05, 2025
```
[CI/Build][AMD][Quantization] Fix test_int8_kernel.py by updating int8_utils to use hip.libdevice.round (#30151)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  dc839ad0
05 Dec, 2025 4 commits
- [Bug] Fix vLLM config is not set error (#29999) · 7b5575fa
  Wentao Ye authored Dec 05, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  7b5575fa
- [Compressed Tensors] Add XPU `wNa16` support (#29484) · 0d8a7d8a
  Yi Liu authored Dec 05, 2025
```
Signed-off-by: yiliu30 <yi4.liu@intel.com>
```
  0d8a7d8a
- [ROCm][MXFP4] Infer w4a4 quant method in rocm aiter fused moe (#29775) · 3628bcaa
  Zhiwei authored Dec 05, 2025
```
Signed-off-by: ZhiweiYan-96 <zhiwei.yan@amd.com>
```
  3628bcaa
- [Perf] Enable separate shared_experts stream only for CUDA (#30085) · 4470ee2f
  Alexander Matveev authored Dec 04, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
  4470ee2f
04 Dec, 2025 4 commits
- Access `partial_rotary_factor` from `rope_parameters` (#29966) · e10c84e0
  Harry Mellor authored Dec 04, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e10c84e0
- [Bugfix] Fix FP8 MoE LoRA (#29890) · 652ba93d
  Jee Jee Li authored Dec 05, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  652ba93d
- [Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145) · 74c4d80c
  wang.yuqi authored Dec 04, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  74c4d80c
- [Misc] Move functions into `PoolingMetadata` (#30027) · 68eb5c8d
  Cyrus Leung authored Dec 04, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  68eb5c8d
03 Dec, 2025 3 commits

[Kernels] Remove BatchedTritonOrDeepGemmExperts and default fallback to Triton (#29929) · 2902c348

bnellnm authored Dec 03, 2025


Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: bnellnm <49004751+bnellnm@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

2902c348

[Performance][DP/EP] Add silu_mul_per_token_group_quant_fp8_colmajor kernel (#29470) · 19bee6d1

Varun Sundar Rabindranath authored Dec 03, 2025

Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

19bee6d1

[refactor] CTMoEMethods to use QuantizationArgs (#28871) · b294e28d

HDCharles authored Dec 03, 2025


Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

b294e28d

02 Dec, 2025 1 commit
- [Attention][CUDAGraph] Remove CG padding from attention backends (#29352) · 1d93f116
  Matthew Bonanni authored Dec 02, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  1d93f116