|
|
b876860c62
|
[Hardware][CPU] Build fix for ARM without BF16 (#21848)
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
|
2025-07-30 06:22:00 -07:00 |
|
|
|
1b0a155534
|
[Perf] Using __nv_fp8_e4m3 instead of c10::e4m3 for per_token_group_quant (#21867)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-29 21:50:46 -06:00 |
|
|
|
ba5c5e5404
|
[Docs] Switch to better markdown linting pre-commit hook (#21851)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-07-29 19:45:08 -07:00 |
|
|
|
12a223ef9b
|
[AMD][CI/Build][Bugfix] Guarding CUDA specific functions by ifndef ROCM (#21766)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2025-07-29 03:35:37 +00:00 |
|
|
|
c6c9122d50
|
[Kernel] SM90 CUTLASS FP8 GEMM: add support for swap AB + kernel tuning (#20396)
Signed-off-by: Faqin Zhong <faqin.zhong@gmail.com>
Co-authored-by: Duncan Moss <djm.moss@gmail.com>
|
2025-07-28 23:13:58 +00:00 |
|
|
|
57c22e57f9
|
Fix CUDA permute/unpermute for use with DeepGemm Moe (#17934)
Signed-off-by: Caleb_Du <Caleb_Du@zju.edu.cn>
|
2025-07-27 07:08:00 -07:00 |
|
|
|
9094d11c5d
|
[Bugfix][Apple Silicon] fix missing symbols when build from source on Mac with Apple Silicon (#21380)
Signed-off-by: Yeju Zhou <yejuzhou@outlook.com>
|
2025-07-26 07:09:57 -07:00 |
|
|
|
75d29cf4e1
|
[Perf] Cuda Kernel for Int8 Per Token Group Quant (#21476)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-25 17:07:07 -07:00 |
|
|
|
136d750f5f
|
[Kernel] Improve machete memory bound perf (#21556)
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
|
2025-07-25 06:53:21 -07:00 |
|
|
|
e8cb0d0495
|
[Bug] Fix Compressed Tensor NVFP4 cutlass_fp4_group_mm illegal memory access (#21465)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-24 08:13:24 -07:00 |
|
|
|
90eeea8f85
|
[Bugfix][ROCm] Fix for warp_size uses on host (#21205)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2025-07-24 00:37:19 -07:00 |
|
|
|
3ec7170ff1
|
[Bugfix][ROCm][Build] Fix build regression on ROCm (#21393)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2025-07-22 20:27:41 -07:00 |
|
|
|
226b452a20
|
Revert "[Refactor] Fix Compile Warning #1444-D (#21208)" (#21384)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-22 08:22:10 -07:00 |
|
|
|
774d0c014b
|
[Perf] Cuda Kernel for Per Token Group Quant (#21083)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-22 07:27:15 -07:00 |
|
|
|
2c8db17cfd
|
[feat]: add SM100 support for cutlass FP8 groupGEMM (#20447)
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-07-22 07:27:12 -07:00 |
|
|
|
4fb56914c5
|
[perf] Add fused MLA QKV + strided layernorm (#21116)
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-07-22 07:07:44 -07:00 |
|
|
|
6e5b5ca580
|
[Refactor] Fix Compile Warning #1444-D (#21208)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-21 23:33:51 -07:00 |
|
|
|
e7b2042681
|
Revert "[Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) (#21334)
Signed-off-by: Ming Yang <minos.future@gmail.com>
|
2025-07-21 21:49:01 -07:00 |
|
|
|
0ec82edda5
|
[perf] Speed up align sum kernels (#21079)
Signed-off-by: Himanshu Jaju <hj@mistral.ai>
|
2025-07-21 11:19:23 -07:00 |
|
|
|
a15a50fc17
|
[CPU] Enable shared-memory based pipeline parallel for CPU backend (#21289)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2025-07-21 09:07:08 -07:00 |
|
|
|
b2eb2b5ad7
|
[Kernel] Apply torch.Tag.needs_fixed_stride_order only for torch==2.6.0 (#19346)
Signed-off-by: rzou <zou3519@gmail.com>
|
2025-07-18 14:10:21 -04:00 |
|
|
|
5780121c95
|
[Perf] Add swap_ab to SM90 FP8 non-block CUTLASS moe grouped gemm (#20911)
Signed-off-by: Shixian Cui <shixian@amazon.com>
Co-authored-by: Shixian Cui <shixian@amazon.com>
|
2025-07-18 04:34:43 +00:00 |
|
|
|
9fb2d22032
|
[Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
|
2025-07-17 09:56:44 -04:00 |
|
|
|
d31a647124
|
[BugFix] Fix import error on non-blackwell machines (#21020)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-07-15 22:27:29 -07:00 |
|
|
|
1eb2b9c102
|
[CI] update typos config for CI pre-commit and fix some spells (#20919)
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
|
2025-07-15 21:12:40 -07:00 |
|
|
|
ed10f3cea1
|
[ROCm] warpSize is being made non constexpr in ROCm 7.0 (#20330)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2025-07-15 14:01:44 -04:00 |
|
|
|
8cdc371217
|
SM100 Cutlass MLA decode with unrestricted num_heads (< 128) for DeepSeek TP (#20769)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
|
2025-07-15 01:06:38 +00:00 |
|
|
|
c488b928a7
|
[ROCm] [Bugfix] [Critical]: Fix mamba compilation bug (#20883)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2025-07-14 15:23:28 +08:00 |
|
|
|
2c11a738b3
|
[Model] New model support for microsoft/Phi-4-mini-flash-reasoning (#20702)
Signed-off-by: Congcong Chen <congcongchen@microsoft.com>
|
2025-07-12 06:02:10 -07:00 |
|
|
|
d47661f0cd
|
[Kernel] Basic tuned configs for NVFP4 CUTLASS dense GEMM (#20646)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-07-11 10:05:33 -06:00 |
|
|
|
5923ab9524
|
[fix]: disable cutlass block scaled group gemm for EP (#20781)
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
|
2025-07-11 02:39:18 +00:00 |
|
|
|
c7753a9809
|
[Hardware][CPU] Vllm int8 quantization enablement for ARM CPU (#14129)
Signed-off-by: nishith-fujitsu <nishith.jaiswal@fujitsu.com>
|
2025-07-10 15:59:04 +00:00 |
|
|
|
47043eb678
|
[Kernel] Triton implementation of causal-conv1d for Mamba-based models (#18218)
Signed-off-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2025-07-09 12:53:55 -07:00 |
|
|
|
5eaf570050
|
Replace multiply_add with homogeneous_multiply_add to Address Clang Template Parameter Issue (#20142)
Signed-off-by: Lu Fang <lufang@fb.com>
|
2025-07-09 00:30:18 +00:00 |
|
|
|
c438183e99
|
[Bugfix] Fix topk_ids indices_type for CUTLASS w8a8 FP8 MoE (#20166)
Signed-off-by: Ming Yang <yming@meta.com>
|
2025-07-08 23:10:57 +00:00 |
|
|
|
40b86aa05e
|
[BugFix] Fix: ImportError when building on hopper systems (#20513)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-07-06 12:17:30 +08:00 |
|
|
|
f73d02aadc
|
[BUG] Fix #20484. Support empty sequence in cuda penalty kernel (#20491)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
|
2025-07-05 19:38:02 -07:00 |
|
|
|
3d184b95b8
|
[feat]: CUTLASS block scaled group gemm for SM100 (#19757)
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Co-authored-by: Duncan Moss <dmoss@nvidia.com>
|
2025-07-04 12:58:04 -06:00 |
|
|
|
783921d889
|
[Perf] Optimize Vectorization Utils for Int 8 Quantization Kernels (#20331)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-07-04 15:06:24 +08:00 |
|
|
|
9e5552aa13
|
[NVIDIA] Support Cutlass w8a8 FP8 for Blackwell Geforce GPUs (sm120) (#17280)
Signed-off-by: kaln27 <liaojuncheng123@foxmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-07-02 06:47:19 -06:00 |
|
|
|
3be8d312a2
|
[Kernel][Bugfix] Fixup some warnings in nvfp4_blockwise_moe when CUDA < 12.8 (#20324)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2025-07-01 18:05:47 -07:00 |
|
|
|
9290de5667
|
remove unused variables in marlin_template.h (#20236)
|
2025-07-02 00:51:52 +00:00 |
|
|
|
6cc1e7d96d
|
[CPU] Update custom ops for the CPU backend (#20255)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2025-07-01 07:25:03 +00:00 |
|
|
|
86debab54c
|
Fix numel() downcast in vllm/csrc/moe/moe_align_sum_kernels.cu +2 (#17082)
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-07-01 06:48:10 +00:00 |
|
|
|
e8c3bd2cd1
|
[Bugfix] Fix some narrowing conversion warnings (#20141)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2025-06-27 09:01:28 -07:00 |
|
|
|
94a55c7681
|
[Fix][ROCm] Remove unused variables to fix build error on GFX11/12 (#19891)
Signed-off-by: Hosang Yoon <hosang.yoon@amd.com>
|
2025-06-27 07:14:44 -07:00 |
|
|
|
0740e29b66
|
[Feature] add quick all reduce (#19744)
Signed-off-by: ilmarkov <imarkov@redhat.com>
Signed-off-by: Haoyang Li <Haoyang.Li@amd.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
|
2025-06-26 20:54:24 -07:00 |
|
|
|
44d2e6af63
|
[Bugfix] Build moe_data for both sm100 and sm90 (#20086)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-06-26 20:50:12 -07:00 |
|
|
|
2d7779f888
|
[Perf] SM100 FP8 GEMM Optimizations after cutlass_profiler (#20071)
Signed-off-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
|
2025-06-26 20:50:09 -07:00 |
|
|
|
0567c8249f
|
[CPU] Fix torch version in x86 CPU backend (#19258)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2025-06-26 03:34:47 -07:00 |
|
