Commits · 333529deae59cd4100df540f225470c9bc539bee · OpenDAS / vllm_cscc

24 Apr, 2026 3 commits
- [EPLB] Fix replica selection bias in fused_moe router (#40810) · 333529de
  Artem Perevedentsev authored Apr 25, 2026
```
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
```
  333529de
- [MoE] Move cutlass moe to fused_moe/experts/ (#40574) · 079a4cf3
  Jackmin801 authored Apr 23, 2026
```
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  079a4cf3
- [MoE] Move remaining PrepareAndFinalize to prepare finalize folder (#39009) · 447c372a
  Jackmin801 authored Apr 23, 2026
```
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
```
  447c372a
22 Apr, 2026 3 commits

[Bugfix] LoRA for DeepSeek V3.2 (#35077) · a250f1bd

ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 authored Apr 22, 2026


Signed-off-by: Hollow Man <hollowman@opensuse.org>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

a250f1bd

[AMD][CI][BugFix] Override normalize_e4m3fn_to_e4m3fnuz for fnuz machines in... · 2463f00f

rasmith authored Apr 21, 2026


[AMD][CI][BugFix] Override normalize_e4m3fn_to_e4m3fnuz for fnuz machines in test_moe_layer_no_parallel (#40550)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>

2463f00f

test: add nan/inf clamp regression test for fused_topk_bias (#40553) · 46794958
Jhao-Ting Chen authored Apr 21, 2026
```
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
```
46794958

21 Apr, 2026 3 commits

[MoE Refactor] Add more MoE layer tests (#39349) · 9db4650e

bnellnm authored Apr 21, 2026

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

9db4650e

[MoE Refactor] Remove SharedFusedMoE class (#35782) · 5e584ce9
bnellnm authored Apr 21, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
5e584ce9
fix: clamp NaN/Inf in topk_softmax to prevent duplicate expert IDs (#39391) · 28c22215
Jhao-Ting Chen authored Apr 21, 2026
```
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
```
28c22215

20 Apr, 2026 2 commits
- Update flashinfer to 0.6.8 (#39959) · 191e3fda
  bai authored Apr 20, 2026
```
Signed-off-by: bai <v@gor.io>
```
  191e3fda
- [MoE Refactor] Move the shared/fused expert output sum into MoERunnerBase (#35949) · 726efe17
  bnellnm authored Apr 20, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  726efe17
19 Apr, 2026 2 commits
- Fix MoE backend selection for LoRA (unquantized MoE) (#40273) · d1135a50
  danisereb authored Apr 19, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  d1135a50
- [FEAT] [Perf] [Gemma4] Fused Gemma4 Routing Function Triton (#39083) · 45232a45
  TJian authored Apr 19, 2026
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  45232a45
18 Apr, 2026 1 commit

[CI] Speed up test_fused_marlin_moe (#40178) · 48a65ccb

Michael Goin authored Apr 17, 2026


Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>

48a65ccb

17 Apr, 2026 2 commits
- Remove outdated tests test_mixtral_moe and test_duplicated_ignored_sequence_group (#40175) · 1f45e837
  Michael Goin authored Apr 17, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  1f45e837
- [Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 (#37463) · a8bffaa1
  Michael Goin authored Apr 17, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  a8bffaa1
16 Apr, 2026 1 commit
- [Bugfix] Temporarily disable B200 fp4 MoE layer tests (#40057) · 79e799eb
  bnellnm authored Apr 16, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  79e799eb
14 Apr, 2026 4 commits

[MoE Refactor] Refactor ZeroExpertFusedMoE into new framework (#35549) · 19ec9a0a
bnellnm authored Apr 14, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
19ec9a0a

[MoE] Move GPT OSS Triton kernel experts into fused_moe/experts/ (#39007) · 1a9353bb

Jackmin801 authored Apr 14, 2026


Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>

1a9353bb

[MoE Refactor] Remove MoE DP chunking (#39107) · e1e318af

bnellnm authored Apr 14, 2026


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

e1e318af

[fix][MOE] Fix MOE experts `intermediate_size` dimension not being narrowed... · 4eee77b8

fxmarty-amd authored Apr 14, 2026


[fix][MOE] Fix MOE experts `intermediate_size` dimension not being narrowed before weight loading (#39688)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>

4eee77b8

13 Apr, 2026 1 commit
- [Bugfix] [Tests] Enforce `out` tensor device in `kernel/moe/test_cutedsl_moe.py` (#39644) · 620e8924
  Yongye Zhu authored Apr 12, 2026
```
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
```
  620e8924
10 Apr, 2026 1 commit
- Add platform manual_seed_all API (#38468) · ec68d53b
  Yan Ma authored Apr 10, 2026
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  ec68d53b
09 Apr, 2026 2 commits

[UX] Integrate DeepGEMM into vLLM wheel via CMake (#37980) · eb4205fe

Michael Goin authored Apr 09, 2026


Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

eb4205fe

[Bugfix] FlashInfer MXINT4 MoE crashes, missing do_finalize (#39315) · 8332078c

Benjamin Chislett authored Apr 08, 2026

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

8332078c

08 Apr, 2026 1 commit

[MoE] Move DEEP_GEMM into experts/ subdirectory (#39005) · a776a48b

Jackmin801 authored Apr 08, 2026


Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

a776a48b

07 Apr, 2026 1 commit
- [Kernels][MoE] Fix legacy_routing to use bitmatrix-based routing path (#38504) · 2df2c85b
  Andreas Karatzas authored Apr 06, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  2df2c85b
06 Apr, 2026 2 commits

[Quantization] Add FlashInfer CuteDSL batched experts backend for NVFP4 MoE (#38251) · e8ebbdde

Yongye Zhu authored Apr 06, 2026


Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

e8ebbdde

[MoE Refactor][Test] FusedMoE layer test (#24675) · f0148240

bnellnm authored Apr 06, 2026


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

f0148240

02 Apr, 2026 2 commits
- [CPU] Support gelu act in cpu_fused_moe (#38770) · c6f722b9
  Li, Jiang authored Apr 02, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  c6f722b9
- Revert "[Kernel] Add gpt-oss Router GEMM kernel (#37205)" (#38778) · 9bd72311
  Xin Yang authored Apr 01, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  9bd72311
01 Apr, 2026 2 commits
- [Kernel] Add MXFP8 to Marlin GEMM/MoE and refactor Mxfp8LinearOp (#34664) · db5d0719
  Michael Goin authored Apr 01, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  db5d0719
- [MoE Refactor] Make SharedExperts class for use with DefaultMoERunner (#35153) · 7cf56a59
  bnellnm authored Apr 01, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  7cf56a59
31 Mar, 2026 3 commits

[MoE Refactor] Migrate Unquantized to Full Oracle Flow (#36286) · d9b90a07

yzong-rh authored Mar 31, 2026


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

d9b90a07

[Bugfix] Fix FusedMoE weight loading with padded hidden dimensions (#37010) · 3896e021
SandishKumarHN authored Mar 31, 2026
```
Signed-off-by: SandishKumarHN <sandish@fb.com>
```
3896e021

replace cuda_device_count_stateless() to current_platform.device_count() (#37841) · 4dfad17e

wliao2 authored Mar 31, 2026


Signed-off-by: Liao, Wei <wei.liao@intel.com>
Signed-off-by: wliao2 <wei.liao@intel.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

4dfad17e

30 Mar, 2026 2 commits
- [EPLB] Optmize eplb mapping and record in router for prefill (#36261) · 12701e8a
  Ilya Markov authored Mar 30, 2026
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
```
  12701e8a
- [NVIDIA] Bugfix NVFP4 DGX Spark and RTX50 (#38423) · b4a2f3ac
  Johnny authored Mar 30, 2026
```
Signed-off-by: johnnynunez <johnnynuca14@gmail.com>
Signed-off-by: Johnny <johnnynuca14@gmail.com>
```
  b4a2f3ac
26 Mar, 2026 2 commits
- [ROCm][CI] Fix AITER state leak in shared_fused_moe_routed_transform test (#38137) · bdc1719e
  Andreas Karatzas authored Mar 26, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  bdc1719e
- Revert "[MoE Kernel] Flashinfer nvfp4 cutedsl moe kernel integration" (#38050) (#38169) · be1a85b7
  Zhewen Li authored Mar 26, 2026
```
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
```
  be1a85b7