NVIDIA/cutlass
1
0
Fork 0
mirror of https://github.com/NVIDIA/cutlass.git synced 2026-07-11 17:48:57 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
e37889f489d2d357aba2367931b8ef02bdd10d19
cutlass/examples/python/CuTeDSL/cute
History
Jiaxuan Bai e37889f489 Fix grouped GEMM with CUTLASS DSL 4.7 (#3369) 
The Hopper grouped GEMM wrapper selected the current NVVM TMA bindings only when the CUTLASS version prefix was exactly 4.6. A 4.7 wheel therefore fell back to the removed CpAsyncBulkTensorLoadMode/loadMode interface.

Detect the TMALoadMode capability directly, preserving the legacy fallback for older bindings. For example, 4.7 now uses the TMALoadMode/mode path and descriptor address-space cast.

Verification: Python syntax compilation and diff checks.
2026-07-08 10:16:39 +08:00
..
ampere
v4.6 tag release. (#3362)
2026-07-06 22:05:33 -04:00
blackwell
v4.6 tag release. (#3362)
2026-07-06 22:05:33 -04:00
blackwell_geforce/kernel
v4.6 dev update. (#3315)
2026-06-15 23:23:20 -04:00
hopper/kernel
Fix grouped GEMM with CUTLASS DSL 4.7 (#3369)
2026-07-08 10:16:39 +08:00
notebooks
v4.6 dev update. (#3315)
2026-06-15 23:23:20 -04:00
tvm_ffi
add fp4_x2 example (#3043)
2026-06-23 17:56:23 +08:00