Commits · 0dfb30d5752950abe72701d98d3e263a75142d43 · OpenDAS / vllm_cscc

10 Feb, 2026 1 commit

support fa kvcache fp8, add VLLM_USE_QUERY_QUANT to not use q quant(todo) · 0dfb30d5

zhuwenwen authored Feb 10, 2026

[opt] 优化epsp代码, 零消耗添加epsp
update VLLM_USE_FUSED_RMS_ROPE=0 (default). for qwen3, VLLM_USE_FUSED_RMS_ROPE=1 (default)
feat(moe/marlin): Marlin W16A16 MoE 自动探测并预打包（去掉手动开关）
perf(qwen3): 融合 q/k RMSNorm + RoPE
fused_moe_fp8接入lmslim

0dfb30d5

13 Oct, 2025 1 commit
- 新增fp8—e5m2 · ed3cdc81
  zhuwenwen authored Oct 13, 2025
  
  ed3cdc81
28 Sep, 2025 2 commits
- 修复kvcache-fp8—e5m2的不能开cp的bug · b2d14ba3
  yangql authored Sep 28, 2025
  
  b2d14ba3
- 新增fp8—e5m2_utils · bb13d854
  yangql authored Sep 28, 2025
  
  bb13d854
16 Jul, 2025 1 commit
- support rms_norm_dynamic_per_token_quant · 91feb245
  zhuwenwen authored Jul 16, 2025
  
  91feb245
06 Jul, 2025 1 commit
- [BugFix] Fix: ImportError when building on hopper systems (#20513) · 40b86aa0
  Lucas Wilkinson authored Jul 06, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  40b86aa0
04 Jul, 2025 2 commits
- [feat]: CUTLASS block scaled group gemm for SM100 (#19757) · 3d184b95
  Duncan Moss authored Jul 04, 2025
```
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Co-authored-by: Duncan Moss <dmoss@nvidia.com>
```
  3d184b95
- [Perf] Optimize Vectorization Utils for Int 8 Quantization Kernels (#20331) · 783921d8
  Wentao Ye authored Jul 04, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  783921d8
02 Jul, 2025 3 commits
- [NVIDIA] Support Cutlass w8a8 FP8 for Blackwell Geforce GPUs (sm120) (#17280) · 9e5552aa
  Joonchen Liau authored Jul 02, 2025
```
Signed-off-by: kaln27 <liaojuncheng123@foxmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  9e5552aa
- [Kernel][Bugfix] Fixup some warnings in nvfp4_blockwise_moe when CUDA < 12.8 (#20324) · 3be8d312
  Tyler Michael Smith authored Jul 01, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  3be8d312
- remove unused variables in marlin_template.h (#20236) · 9290de56
  周周周 authored Jul 02, 2025
  
  9290de56
27 Jun, 2025 3 commits
- [Bugfix] Fix some narrowing conversion warnings (#20141) · e8c3bd2c
  Tyler Michael Smith authored Jun 27, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  e8c3bd2c
- [Bugfix] Build moe_data for both sm100 and sm90 (#20086) · 44d2e6af
  Michael Goin authored Jun 27, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  44d2e6af
- [Perf] SM100 FP8 GEMM Optimizations after cutlass_profiler (#20071) · 2d7779f8
  Ilya Markov authored Jun 27, 2025
```
Signed-off-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  2d7779f8
16 Jun, 2025 2 commits
- [Kernel] GGUF MMVQ kernel for multiple input vectors (#18754) · dec66d25
  Szymon Ożóg authored Jun 16, 2025
```
Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>
```
  dec66d25
- [MISC] Remove unused variableds in C++ (#19609) · c6703d1e
  Lu Fang authored Jun 16, 2025
```
Signed-off-by: Lu Fang <lufang@fb.com>
```
  c6703d1e
15 Jun, 2025 1 commit
- [Perf] Further tunings for SM100 FP8 CUTLASS kernel (#19566) · e13945f9
  Ilya Markov authored Jun 15, 2025
  
  e13945f9
14 Jun, 2025 1 commit
- [Hardware][NVIDIA][kernel] Fp4 MOE quant kernel optimization (#19500) · 294fc1e2
  jiahanc authored Jun 14, 2025
  
  294fc1e2
12 Jun, 2025 3 commits
- [Perf] Vectorize static / dynamic INT8 quant kernels (#19233) · b6efafd9
  Wentao Ye authored Jun 12, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  b6efafd9
- add kvcache fp8 · 504a12b8
  zhuwenwen authored Jun 12, 2025
  
  504a12b8
- [CI] change spell checker from codespell to typos (#18711) · 2f1c19b2
  Ning Xie authored Jun 12, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  2f1c19b2
07 Jun, 2025 1 commit

[Kernel] Integrate CUTLASS MoE kernel with PPLX (#18762) · 84166fee

ElizaWszola authored Jun 07, 2025


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

84166fee

05 Jun, 2025 1 commit
- [Hardware][NVIDIA] FP4 MoE kernel optimization (#19110) · 61059bee
  Chiyue Wei authored Jun 05, 2025
```
Signed-off-by: Chiyue Wei <chiyuew@nvidia.com>
Co-authored-by: Chiyue Wei <chiyuew@nvidia.com>
```
  61059bee
04 Jun, 2025 2 commits
- [Perf] Tunings for SM100 FP8 CUTLASS kernel (#18778) · 53a5a0ce
  Michael Goin authored Jun 04, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  53a5a0ce
- Sm100 blockwise fp8 swap ab (#18564) · 5f2cd251
  Lain authored Jun 04, 2025
  
  5f2cd251
03 Jun, 2025 2 commits
- [Perf] Tune `scaled_fp8_quant` by increasing vectorization (#18844) · e31446b6
  Michael Goin authored Jun 03, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  e31446b6
- [Misc] Add SPDX-FileCopyrightText (#19100) · 02f0c7b2
  Simon Mo authored Jun 03, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  02f0c7b2
22 May, 2025 1 commit

[Build/CI] Fix CUDA 11.8 build (#17679) · 6e588da0

Tyler Michael Smith authored May 22, 2025


Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>

6e588da0

16 May, 2025 2 commits
- [Bugfix] fix `an illegal memory access was encountered` of marlin kernel + act_order (#18245) · e73b7dfd
  Jinzhen Lin authored May 17, 2025
  
  e73b7dfd
- use ceil_div in cutlass block scaling shape check (#17918) · e23564cb
  Lain authored May 16, 2025
  
  e23564cb
14 May, 2025 2 commits
- [AMD][torch.compile] Enable silu+fp8_quant fusion for rocm (#18082) · 7b2f28de
  Charlie Fu authored May 14, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  7b2f28de
- add kvint8 · 45273722
  xiabo authored May 14, 2025
  
  45273722
13 May, 2025 2 commits
- Fix Broken macro for cutlass moe (#18049) · e57e4d6e
  Driss Guessous authored May 12, 2025
```
Signed-off-by: drisspg <drisspguessous@gmail.com>
```
  e57e4d6e
- [ROCm]: Fix build from source failure with gcc14 and ROCm 6.3 (#13779) · d8487ef5
  Arjun Kathuria authored May 13, 2025
```
Signed-off-by: Arjun Kathuria <arjun.kathuria8@gmail.com>
```
  d8487ef5
11 May, 2025 1 commit
- [Kernel] fp4 marlin kernel (#17687) · d74e5f37
  Jinzhen Lin authored May 11, 2025
```
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
```
  d74e5f37
09 May, 2025 1 commit
- [Hardware/NVIDIA/Kernel] Enable nvidia/DeepSeek-R1-FP4 Model (#16362) · 0c0fdae8
  Pavani Majety authored May 09, 2025
  
  0c0fdae8
08 May, 2025 2 commits
- Add cutlass support for blackwell fp8 blockwise gemm (#14383) · 376786fa
  Shu Wang authored May 08, 2025
```
Signed-off-by: Shu Wang <shuw@nvidia.com>
```
  376786fa
- [Easy] Eliminate c10::optional usage in vllm/csrc (#17819) · f50dcb7c
  Lu Fang authored May 08, 2025
  
  f50dcb7c
07 May, 2025 2 commits

[Kernel] GGUF MoeVec kernel (#16780) · 1a45a613

Szymon Ożóg authored May 07, 2025


Signed-off-by: SzymonOzog <szymon.ozog@aleph-alpha.com>
Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>

1a45a613

Removed unused marlin cuda code (#17684) · a17cef70
Michael Goin authored May 06, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
a17cef70