Commits · 6f1beee648521f56b02cd2b37e727b368a9732dc · OpenDAS / vllm_cscc

25 Mar, 2026 1 commit
- Update modelopt.py · 6f1beee6
  zhuwenwen authored Mar 25, 2026
  
  6f1beee6
24 Mar, 2026 1 commit
- sync v0.18.0 · eefa41c1
  zhuwenwen authored Mar 24, 2026
  
  eefa41c1
18 Mar, 2026 1 commit

Fix eplb nvfp4 experts hook (#37217) · cdcffafe

Elvir Crnčević authored Mar 16, 2026


Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Signed-off-by: Elvir Crncevic <elvir@anthropic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
(cherry picked from commit fd4d9630)

cdcffafe

13 Mar, 2026 3 commits
- [ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316) · 6341d430
  Divakar Verma authored Mar 13, 2026
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
  6341d430
- [2/N] Elastic EP Milestone 2: Integrating NIXL-EP (#35627) · d5af196c
  Itay Alroy authored Mar 13, 2026
```
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>
```
  d5af196c
- [MoE] Add routing simulation override for MXFP4 quantized MoE (#33595) · aaa3092f
  Jaewon authored Mar 12, 2026
```
Signed-off-by: Jaewon Lee <jaewon@meta.com>
```
  aaa3092f
12 Mar, 2026 1 commit
- [UX] Only show FP4 Marlin fallback warning for w4a4 models (#36806) · 57431d82
  Michael Goin authored Mar 12, 2026
```
Co-authored-by: Claude <noreply@anthropic.com>
```
  57431d82
11 Mar, 2026 1 commit
- [Doc] Fix duplicate words in comments (#36713) · 4bf53362
  Hongbin Guo authored Mar 11, 2026
```
Signed-off-by: Hongbin10 <jdmjdm1998@163.com>
```
  4bf53362
08 Mar, 2026 1 commit
- Add support for ModelOpt MXFP8 MoE models (#35986) · 0a6a3a12
  danisereb authored Mar 08, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  0a6a3a12
05 Mar, 2026 1 commit

[Bugfix][CI] fix typos (#34934) · 6a895197

Jiayi Yan authored Mar 06, 2026

Signed-off-by: 1195343015 <1195343015@qq.com>
Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

6a895197

04 Mar, 2026 2 commits
- [Hardware] Replace `torch.cuda.empty_cache` with `torch.accelerator.empty_cache` (#30681) · 16d2ad1d
  Kunshang Ji authored Mar 04, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  16d2ad1d
- [ROCm][Bugfix] Fall back from CK MXFP4 MoE when GEMM dimensions are unsupported (#35893) · 5dc35387
  Chuan (Richard) Li authored Mar 04, 2026
```
Signed-off-by: Li <chuali@amd.com>
```
  5dc35387
03 Mar, 2026 2 commits

[Bugfix] Fix misnamed parameter in compressed_tensors_moe.py (#35813) · a9b8b13e

bnellnm authored Mar 03, 2026


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

a9b8b13e

[MoE Refactor] Create MK for TRTLLM Kernels (#32564) · 97995f63

Robert Shaw authored Mar 03, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>

97995f63

02 Mar, 2026 1 commit
- [XPU] fix mxfp4 activation type (#35691) · 92f5d0f0
  Kunshang Ji authored Mar 02, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  92f5d0f0
01 Mar, 2026 1 commit
- fix(mxfp4): return is_monolithic=False when LoRA is enabled for Triton backend (#35382) · 5a435507
  Seungho Yoon authored Mar 01, 2026
```
Signed-off-by: Seungho Yoon <yoonsnowdev@gmail.com>
```
  5a435507
28 Feb, 2026 1 commit

[ROCm][Quantization] Add Composable Kernel (CK) backend support for M… (#34301) · d5b6f3ba

Douglas Lehr authored Feb 27, 2026


Signed-off-by: Doug Lehr <douglehr@amd.com>
Signed-off-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Signed-off-by: Douglas Lehr <Doug.Lehr@amd.com>
Co-authored-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>

d5b6f3ba

26 Feb, 2026 7 commits
- [Bugfix] Fix KV Scale loading for MLA Models (#35430) · 62830211
  Pavani Majety authored Feb 26, 2026
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  62830211
- [ROCm][Quantization] GPT OSS Upstream MoE wmxfp4_afp8 with static scales (#30357) · 01923eec
  Aleksandr Malyshev authored Feb 26, 2026
```
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
```
  01923eec
- [WideEP] Remove pplx all2all backend (#33724) · eb19955c
  Tyler Michael Smith authored Feb 26, 2026
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  eb19955c
- add mixed precision support for modelopt (#35047) · d0105b84
  sychen52 authored Feb 26, 2026
```
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
```
  d0105b84
- [ROCm] Add dynamic mxfp4 quantization for DeepSeek V2 projection layers (#34157) · ec8ab9d2
  Douglas Lehr authored Feb 26, 2026
```
Signed-off-by: Doug Lehr <douglehr@amd.com>
Signed-off-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Co-authored-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
```
  ec8ab9d2
- [Refactor] Remove dead or duplicate func utils or variables (#35318) · 05972ea7
  Wentao Ye authored Feb 26, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  05972ea7
- [MoE Refactor] MXFP4 Cutlass Experts to MK (#34542) · 1976356e
  Yongye Zhu authored Feb 25, 2026
```
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
```
  1976356e
25 Feb, 2026 1 commit
- [Platform] Add current_platform.num_compute_units interface (#35042) · 8ad54a99
  Kunshang Ji authored Feb 25, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
```
  8ad54a99
24 Feb, 2026 5 commits

Integrate flashinfer mm_mxfp8 in ModelOpt MXFP8 (#35053) · 9609b1f1
danisereb authored Feb 24, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
9609b1f1
Fix fallback to default tactic (flashinfer autotuner) with trtllm_fp4_block_scale_moe (#35088) · a0c70816
danisereb authored Feb 24, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
a0c70816

[Attn,KV-cache] Use per-head scales in the attention selector (#34281) · a87cc508

Eldar Kurtić authored Feb 24, 2026


Signed-off-by: Your Name <you@example.com>
Signed-off-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Your Name <you@example.com>

a87cc508

[Refactor] [1/N] Reorganize kernel abstraction directory (#34055) · 6af03f23

BadrBasowid authored Feb 24, 2026


Signed-off-by: BadrBasowid <badr.basowid@gmail.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

6af03f23

[Quantization] Support FP8 MoE bias for models like GPT-OSS (#34906) · ec853405

Jia Guo authored Feb 23, 2026


Signed-off-by: jasperjiaguo <jasperg662@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

ec853405

23 Feb, 2026 1 commit
- [kv-cache, ct] Use compressed-tensors as a source of ground-truth for quant strategies (#34254) · b95bb692
  Eldar Kurtić authored Feb 23, 2026
```
Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
```
  b95bb692
22 Feb, 2026 1 commit

[Model] Add NVFP4 quantization support for Step3.5-Flash (#34478) · b7892a3b

tacos8me authored Feb 22, 2026


Signed-off-by: tacos8me <ian@cloudhabit.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>