Commits · 18f030d940250f54dce478b6a67ac3755c2b3daf · OpenDAS / vllm_cscc

"csrc/quantization/w8a8/fp8/nvidia/quant_utils.cuh" did not exist on "cbbc904470668b9420e71595edeef76d673a2d59"

21 Jun, 2025 2 commits
- update torch2.5 · 675d3e87
  zhuwenwen authored Jun 21, 2025
  
  675d3e87
- fix build error · e87de76c
  zhuwenwen authored Jun 21, 2025
  
  e87de76c
09 Jun, 2025 1 commit
- [Fix] Allow kernel compilation for CUDA capability 8.7 (#19328) · 59abbd84
  Conroy Cheers authored Jun 09, 2025
```
Signed-off-by: Conroy Cheers <conroy@corncheese.org>
```
  59abbd84
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

04 Jun, 2025 1 commit
- [KERNEL] Sampler. CUDA kernel for applying repetition penalty (#18437) · 5d6d1adf
  Vadim Gimpelson authored Jun 04, 2025
  
  5d6d1adf
03 Jun, 2025 1 commit
- [ROCm][Build] Clean up the ROCm build (#19040) · 9e6f61e8
  Gregory Shtrasberg authored Jun 02, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  9e6f61e8
28 May, 2025 1 commit
- [Build] Fixes for CMake install (#18570) · a3896c7f
  Luka Govedič authored May 27, 2025
  
  a3896c7f
27 May, 2025 2 commits
- [feat]适配sgl moe_fused_gate kernel · 0b229519
  王敏 authored May 27, 2025
  
  0b229519
- feat(rocm-support): support mamba2 on rocm (#18565) · a547aeb8
  almersawi authored May 27, 2025
```
Signed-off-by: Islam Almersawi <islam.almersawi@openinnovation.ai>
Co-authored-by: Islam Almersawi <islam.almersawi@openinnovation.ai>
```
  a547aeb8
23 May, 2025 1 commit
- [Bugfix][Build/CI] Fixup CUDA compiler version check for CUDA_SUPPORTED_ARCHS (#18579) · 1068556b
  Simon Mo authored May 23, 2025
  
  1068556b
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

20 May, 2025 1 commit
- support Z100L and K100 inference · a5aa55e8
  zhuwenwen authored May 20, 2025
  
  a5aa55e8
15 May, 2025 1 commit
- [Build] Allow shipping PTX on a per-file basis (#18155) · c7852a6d
  Lucas Wilkinson authored May 15, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  c7852a6d
13 May, 2025 1 commit
- Implements dual-chunk-flash-attn backend for dual chunk attention with sparse... · 60f76243
  Tao He authored May 13, 2025
```
Implements dual-chunk-flash-attn backend for dual chunk attention with sparse attention support (#11844)
```
  60f76243
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 1 commit
- 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
05 May, 2025 2 commits
- [Kernel] some optimizations for dense marlin and moe marlin (#16850) · 1d0c9d6b
  Jinzhen Lin authored May 06, 2025
```
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
```
  1d0c9d6b
- [Build/CI] Upgrade CUTLASS to 3.9.2 (#17641) · f62cad64
  Tyler Michael Smith authored May 04, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  f62cad64
03 May, 2025 1 commit
- [Build/CI] Upgrade CUTLASS to 3.9.1 (#17602) · c8386fa6
  Tyler Michael Smith authored May 03, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  c8386fa6
02 May, 2025 1 commit
- permute/unpermute kernel for moe optimization (#14568) · 3e887d2e
  Caleb_Du authored May 03, 2025
```
Signed-off-by: Caleb_Du <Caleb_Du@zju.edu.cn>
```
  3e887d2e
01 May, 2025 1 commit

[torch.compile] Add torch inductor pass for fusing silu_and_mul with... · 460a2b11

Sage Moore authored May 01, 2025


[torch.compile] Add torch inductor pass for fusing silu_and_mul with subsequent scaled_fp8_quant operations (#10867)
Signed-off-by: Sage Moore <sage@neuralmagic.com>

460a2b11

30 Apr, 2025 1 commit
- Update PyTorch to 2.7.0 (#16859) · 2c4f59af
  Huy Do authored Apr 29, 2025
  
  2c4f59af
27 Apr, 2025 1 commit
- [NVIDIA] Support Cutlass MLA for Blackwell GPUs (#16032) · ed7a29d9
  Kaixi Hou authored Apr 27, 2025
```
Signed-off-by: kaixih <kaixih@nvidia.com>
```
  ed7a29d9
22 Apr, 2025 1 commit
- [Performance][ROCm] Add skinny gemms for unquantized linear on ROCm (#15830) · 188b7f9b
  Charlie Fu authored Apr 21, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
```
  188b7f9b
15 Apr, 2025 1 commit

[Kernel] moe wna16 marlin kernel (#14447) · d06ba4ed

Jinzhen Lin authored Apr 15, 2025


Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

d06ba4ed

11 Apr, 2025 1 commit
- [Kernel] support merge_attn_states CUDA kernel, 3x speedup (#16173) · e9528f6d
  DefTruth authored Apr 11, 2025
```
Signed-off-by: DefTruth <qiustudent_r@163.com>
```
  e9528f6d
01 Apr, 2025 1 commit
- [Distributed] Add custom allreduce support for ROCM (#14125) · b7b7676d
  Ilya Markov authored Apr 01, 2025
```
Signed-off-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  b7b7676d
31 Mar, 2025 3 commits
- Move dockerfiles into their own directory (#14549) · e6e3c55e
  Harry Mellor authored Mar 31, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e6e3c55e
- [V1] Fully Transparent Implementation of CPU Offloading (#15354) · 555aa219
  youkaichao authored Mar 31, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  555aa219
- skip fp8 kernels and paged_attention_rocm · 52675626
  zhuwenwen authored Mar 31, 2025
  
  52675626
29 Mar, 2025 1 commit
- [ROCm][AMD][Build] Update AMD supported arch list (#15632) · c802f543
  Gregory Shtrasberg authored Mar 28, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  c802f543
27 Mar, 2025 1 commit

[Kernel] CUTLASS grouped gemm fp8 MoE kernel (#13972) · 9239bf71

ElizaWszola authored Mar 27, 2025


Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>

9239bf71

14 Mar, 2025 2 commits

Update to torch==2.6.0 (#12721) · 14f301b5

Michael Goin authored Mar 14, 2025


Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: luka <luka@neuralmagic.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

14f301b5

[Bugfix][Kernel]: Fix AllSpark kernel compilation errors and enable for CUDA < 12.0 (#14430) · 977a1677
Yajie Wang authored Mar 15, 2025
```
Signed-off-by: wyj371990 <wyj371990@alibaba-inc.com>
```
977a1677

12 Mar, 2025 2 commits
- [FEAT] [ROCm] [Embedding] Add encoder-only model support into ROCm Flash... · 916836bb
  TJian authored Mar 13, 2025
```
[FEAT] [ROCm] [Embedding] Add encoder-only model support into ROCm Flash Attention to enable embedding models. (#14664)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  916836bb
- [ROCm][Bugfix] Ensure that the moe_wna16_gemm kernel is not built on ROCm platforms. (#14629) · 45f3f3f5
  Sage Moore authored Mar 12, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  45f3f3f5
11 Mar, 2025 2 commits
- [BugFix/Build] Fix sparse kernels not getting built on hopper (#14572) · 07b4b7a3
  Lucas Wilkinson authored Mar 11, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  07b4b7a3
- [Kernel] moe wna16 cuda kernel (#13321) · 90e88ab7
  Jinzhen Lin authored Mar 11, 2025
```
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  90e88ab7
08 Mar, 2025 1 commit

[Build/BugFix] Fix hopper 12.8 build (#14354) · 7caff01a

Lucas Wilkinson authored Mar 08, 2025


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

7caff01a

05 Mar, 2025 1 commit
- Disable GPTQ AllSpark kernels for CUDA Compiler < 12.0 (#14157) · e123aafd
  Michael Goin authored Mar 04, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  e123aafd