Skip to content

Actions: NVIDIA/cutlass

Auto Assign New Issues to Triage Project

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
588 workflow runs
588 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[BUG][QST] Hopper Grouped GEMM Fails When Workspace not aligned at 64, but MinWorkspaceAlignment =16
Auto Assign New Issues to Triage Project #974: Issue #2042 opened by ankutalev
January 16, 2025 12:40 17s
January 16, 2025 12:40 17s
[BUG] Modifying the block/warptile shapes and the output datatype in the unit test causes the tests to fail.
Auto Assign New Issues to Triage Project #973: Issue #2041 opened by xiaonans
January 16, 2025 05:37 12s
January 16, 2025 05:37 12s
[BUG]MMA FP8
Auto Assign New Issues to Triage Project #972: Issue #2040 opened by SunNy820828449
January 16, 2025 02:56 14s
January 16, 2025 02:56 14s
[QST]Conv3d with hopper.
Auto Assign New Issues to Triage Project #971: Issue #2039 opened by SunNy820828449
January 14, 2025 13:12 15s
January 14, 2025 13:12 15s
[QST] link invalid in efficient_gemm.md
Auto Assign New Issues to Triage Project #970: Issue #2038 opened by unship
January 13, 2025 09:06 11s
January 13, 2025 09:06 11s
[QST] Will CUTLASS be open to third-party devices? Can third-party devices add relevant code logic to it?
Auto Assign New Issues to Triage Project #969: Issue #2036 opened by Shan19900305
January 12, 2025 16:19 14s
January 12, 2025 16:19 14s
[QST]Question about the picture in documentation Efficient GEMM in CUDA
Auto Assign New Issues to Triage Project #968: Issue #2034 opened by sleepwalker2017
January 9, 2025 03:28 13s
January 9, 2025 03:28 13s
[FEA] FP8 sparse tensor cores support A(row+dense) x B(sparse) = C(row+dense)
Auto Assign New Issues to Triage Project #967: Issue #2032 opened by zhink
January 8, 2025 08:10 14s
January 8, 2025 08:10 14s
[QST]CUTLASS support for fp8 sparse matrix(for W) multiplication for A*W=Y with GPU(SM90a/89)sparse tensor core
Auto Assign New Issues to Triage Project #966: Issue #2029 opened by zhink
January 7, 2025 12:21 12s
January 7, 2025 12:21 12s
[BUG] Logic issue in nondeterministic reduction mode of Stream-K tile scheduler.
Auto Assign New Issues to Triage Project #965: Issue #2027 opened by allispaul
January 7, 2025 00:52 9s
January 7, 2025 00:52 9s
[QST] What is API version compatibility?
Auto Assign New Issues to Triage Project #964: Issue #2025 opened by ZzEeKkAa
January 6, 2025 20:02 16s
January 6, 2025 20:02 16s
[QST] why have Int<2>{} in coalesce_x function when last shape value equal to constant one.
Auto Assign New Issues to Triage Project #963: Issue #2023 opened by Shan19900305
January 5, 2025 16:53 12s
January 5, 2025 16:53 12s
[QST] why the implementation of f16xs8 mixed gemm is different between TRT-LLM and native cutlass mixed gemm example?
Auto Assign New Issues to Triage Project #962: Issue #2022 opened by danielhua23
January 5, 2025 13:16 10s
January 5, 2025 13:16 10s
[QST] The code location where the shared memory write by swizzled layout occurs in cutlass 2.x?
Auto Assign New Issues to Triage Project #961: Issue #2019 opened by danielhua23
January 1, 2025 03:08 15s
January 1, 2025 03:08 15s
[QST] Why it won't OOB in tiled_copy pipeline
Auto Assign New Issues to Triage Project #960: Issue #2018 opened by ZhZhang711
December 31, 2024 09:09 14s
December 31, 2024 09:09 14s
[BUG] Memory corruption/undefined behavior on GemmUniversal in 3.4.0 - 3.6.0 🐛
Auto Assign New Issues to Triage Project #959: Issue #2017 opened by warpuv
December 28, 2024 17:47 11s
December 28, 2024 17:47 11s
[QST] Where is CuTe ValLayout in TiledMMA as of CUTLASS 3.4.0
Auto Assign New Issues to Triage Project #958: Issue #2016 opened by ZhZhang711
December 27, 2024 10:55 15s
December 27, 2024 10:55 15s
[QST]Why Does CUTLASS Use 3-4-3 Swizzle?
Auto Assign New Issues to Triage Project #957: Issue #2015 opened by ziyuhuang123
December 27, 2024 04:02 11s
December 27, 2024 04:02 11s
[BUG] Precision issue with python cutlass gemm
Auto Assign New Issues to Triage Project #956: Issue #2014 opened by MinghaoYan
December 26, 2024 19:03 17s
December 26, 2024 19:03 17s
[BUG] Where is 3.6.0 release?
Auto Assign New Issues to Triage Project #955: Issue #2012 opened by ankutalev
December 25, 2024 10:00 13s
December 25, 2024 10:00 13s
[QST] why kElementsPerAccess > 1 is not permanent in default_mma_sm80_core.h
Auto Assign New Issues to Triage Project #954: Issue #2011 opened by danielhua23
December 23, 2024 12:33 12s
December 23, 2024 12:33 12s
[BUG] [QST] Regression - why Sm90RowBroadcast in 3.5.1 stops support smem usage?
Auto Assign New Issues to Triage Project #953: Issue #2010 opened by ankutalev
December 23, 2024 10:11 14s
December 23, 2024 10:11 14s
[BUG] Removal of OpMultiplyAdd template substitutions from mma_sm80.h in 3.5.1
Auto Assign New Issues to Triage Project #952: Issue #2009 opened by ankutalev
December 23, 2024 10:03 16s
December 23, 2024 10:03 16s
[QST]How Does TMA Work in CUTLASS for Writing from Shared Memory to Global Memory?
Auto Assign New Issues to Triage Project #951: Issue #2008 opened by ziyuhuang123
December 23, 2024 07:13 13s
December 23, 2024 07:13 13s
[QST] How to Let __launch_bounds__ and setmaxnreg Work with Each Other?
Auto Assign New Issues to Triage Project #950: Issue #2007 opened by Maximilianxu
December 23, 2024 03:12 10s
December 23, 2024 03:12 10s