Commits · 934acddef9fa4eb1b6cc897d2e39db77385539c6 · OpenDAS / vllm_cscc

13 Feb, 2026 1 commit
- [Perf] fused_moe: add int4_w4a16 benchmark support and tuning config (#34130) · 934acdde
  Matthias Gehre authored Feb 13, 2026
```
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  934acdde
12 Feb, 2026 2 commits

[Attention] Add FlashInfer Sparse MLA backend (#33451) · f2c47886

Matthew Bonanni authored Feb 12, 2026


Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

f2c47886

[Refactor] Replace `activation: str` with `MoEActivation` enum (#33843) · ff1f83b0
Michael Goin authored Feb 11, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
```
ff1f83b0

11 Feb, 2026 1 commit
- [Bugfix] Fix benchmark_moe.py inplace assertion with torch >= 2.9 (#34149) · 7a048ee6
  Matthias Gehre authored Feb 11, 2026
```
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
```
  7a048ee6
09 Feb, 2026 3 commits
- [Kernel] FlashInfer: switch allreduce fusion to unified API (#33985) · d4f123cc
  Mohammad Miadh Angkad authored Feb 09, 2026
```
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
```
  d4f123cc
- [Misc] Fix up attention benchmarks (#33810) · d0d97e29
  Lucas Wilkinson authored Feb 09, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
```
  d0d97e29
- [Model] GLM adaptation (#34124) · 978a37c8
  Jee Jee Li authored Feb 09, 2026
  
  978a37c8
06 Feb, 2026 2 commits
- [Refactor] Remove align block size logic in `moe_permute` (#33449) · 77c09e11
  Wentao Ye authored Feb 06, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  77c09e11
- [Docs] Update link to Benchmark CLI documentation (#33254) · 5c52644b
  Eldar Kurtić authored Feb 06, 2026
```
Signed-off-by: Eldar Kurtić <8884008+eldarkurtic@users.noreply.github.com>
```
  5c52644b
02 Feb, 2026 1 commit
- Add unpermute-aware fused MoE LoRA path (#32655) · 7320ca39
  Runkai Tao authored Feb 01, 2026
```
Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
```
  7320ca39
31 Jan, 2026 2 commits

[Misc] Replace deprecated interface seed_everything (#33474) · 68feb76a
Roy Wang authored Jan 31, 2026
```
Signed-off-by: esmeetu <jasonailu87@gmail.com>
```
68feb76a

Add support for Mistral Large 3 inference with Flashinfer MoE (#33174) · f0bca83e

Dimitrios Bariamis authored Jan 31, 2026

Signed-off-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
Co-authored-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

f0bca83e

28 Jan, 2026 3 commits

[Quantization][Deprecation] Remove Marlin 24 (#32688) · af9b69f9

Robert Shaw authored Jan 28, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

af9b69f9

[Quantization][Deprecation] Remove BitBlas (#32683) · 247d1a32

Robert Shaw authored Jan 28, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>

247d1a32

Add attention benchmarking tools (#26835) · e82fa448

Matthew Bonanni authored Jan 27, 2026


Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>

e82fa448

27 Jan, 2026 2 commits

[AMD][QWEN3-NEXT] FP8 Tunings (#32042) · da8d0c44
Lifan Shen authored Jan 27, 2026
```
Signed-off-by: Lifan Shen <lifans@meta.com>
```
da8d0c44

[MoE Refactor] Integrate Naive Prepare Finalize into MK (#32567) · 5a93b916

Robert Shaw authored Jan 26, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: amirkl94 <203507526+amirkl94@users.noreply.github.com>

5a93b916

26 Jan, 2026 1 commit
- [Refactor] Remove unused `_moe_permute` function (#33108) · 8f987883
  Wentao Ye authored Jan 26, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  8f987883
25 Jan, 2026 1 commit
- [Perf][Kernel] Optimize FP4 quantization kernels (SM100F) (#32520) · fcb9df99
  Roberto L. Castro authored Jan 25, 2026
```
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
```
  fcb9df99
23 Jan, 2026 2 commits
- [Refactor] Rename `gptq_marlin` to `marlin` to match MoE (#32952) · 4561f139
  Michael Goin authored Jan 23, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  4561f139
- [Bug] Fix benchmark script `moe_permute_unpermute` (#32949) · dfab5f37
  Wentao Ye authored Jan 23, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  dfab5f37
22 Jan, 2026 1 commit
- [Perf] Create TMA-aligned input scale tensor for DeepGemm on Hopper (#32619) · d08b356e
  Xin Yang authored Jan 22, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  d08b356e
21 Jan, 2026 4 commits
- [Kernel] Add topk_sigmoid kernel (#31246) · 63227acc
  Xin Yang authored Jan 21, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  63227acc
- Add missing import of fused_topk to benchmark_moe (#32784) · f9995398
  danisereb authored Jan 21, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  f9995398
- [PluggableLayer][1/N] Define PluggableLayer (Fix ci) (#32744) · 1861ae8a
  whx authored Jan 22, 2026
```
Signed-off-by: whx-sjtu <2952154980@qq.com>
```
  1861ae8a
- [MoE Refactor] Oracle Select FP8+NVFP4 Kernels In Priority (#32414) · 42135d68
  Robert Shaw authored Jan 21, 2026
  
  42135d68
19 Jan, 2026 1 commit

[GLM-4.7] GLM Model support for GLM-Lite (#31386) · 71832ba7

Yuxuan Zhang authored Jan 19, 2026


Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: Yuxuan Zhang <2448370773@qq.com>

71832ba7

12 Jan, 2026 1 commit
- [cpu][bench] Add Fused MoE Micro Benchmark for CPU Backend (#32092) · 5e034f2e
  Andika Rachman authored Jan 12, 2026
```
Signed-off-by: andikarachman <andika.rachman.y@gmail.com>
```
  5e034f2e
09 Jan, 2026 2 commits
- [1/N][Attention] Restructure attention: move files (#31916) · 2612ba92
  Matthew Bonanni authored Jan 09, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  2612ba92
- [Cleanup] Remove obsolete spec decoding compatibility logic (#32003) · 29ce4822
  Nick Hill authored Jan 08, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  29ce4822
08 Jan, 2026 2 commits

[MoE Refactor][16/N] Apply Refactor to NVFP4 (#31692) · 9f6dcb71

Robert Shaw authored Jan 07, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>

9f6dcb71

[MoE Refactor][15/N] Apply Refactor to Fp8 (#31415) · 5dcd7ef1
Robert Shaw authored Jan 07, 2026

5dcd7ef1

07 Jan, 2026 1 commit

[Misc] Improve error messages for unsupported types and parameters (#30593) · 0790f076

BlankR authored Jan 07, 2026


Signed-off-by: BlankR <hjyblanche@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

0790f076

06 Jan, 2026 3 commits
- [Misc] Use `deprecated` for `seed_everything` (#31780) · db318326
  Cyrus Leung authored Jan 06, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  db318326
- [cpu][bench] Add CPU paged attention benchmarks (#31720) · 799b5721
  Fadi Arafeh authored Jan 06, 2026
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  799b5721
- [Bugfix] Add init_workspace_manager to moe kernel benchmarks (#31042) · e1cd7a5f
  Michael Goin authored Jan 05, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  e1cd7a5f
02 Jan, 2026 1 commit
- [Benchmark] Fix OOM during MoE kernel tuning for large models (#31604) · a0e9ee83
  Alfred authored Jan 03, 2026
```
Signed-off-by: Alfred <massif0601@gmail.com>
```
  a0e9ee83
25 Dec, 2025 1 commit

use the same stream for cuda graph catpure and replay for NCCL (#29207) · 030fc449

Amir Samani authored Dec 25, 2025


Signed-off-by: Amir Samani <asamani@nvidia.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

030fc449

23 Dec, 2025 1 commit
- [Chore] Update more locations to use `attention_config.backend` (#31153) · 8cef1376
  Cyrus Leung authored Dec 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  8cef1376
21 Dec, 2025 1 commit
- [NVFP4][Perf] Tune NVFP4 input quant kernel for small batch size (#30897) · 06d49028
  Michael Goin authored Dec 21, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  06d49028