mirror of
https://github.com/NVIDIA/cutlass.git
synced 2026-05-11 00:40:03 +00:00
v3.9 update (#2203)
* v3.9 update * voidD --------- Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
@@ -10025,7 +10025,8 @@ def GenerateSM120_TensorOp_fp4_UMMA_gemm_with_block_scaled(manifest, cuda_versio
|
||||
|
||||
tile_sizes_cooperative = [
|
||||
[128, 128, 128],
|
||||
[128, 128, 256]
|
||||
[128, 128, 256],
|
||||
[256, 128, 128]
|
||||
]
|
||||
|
||||
tile_sizes_pingpong = [
|
||||
|
||||
Reference in New Issue
Block a user