bssrdf
|
ba70ad8e59
|
added test cases exactly replicating sdxl unet steps
|
2025-11-06 20:35:37 -05:00 |
|
bssrdf
|
311213d209
|
make sure there are enough channels for split-k
|
2025-11-06 10:21:49 -05:00 |
|
bssrdf
|
09e3a5f07d
|
try to reduce index calculation
|
2025-11-05 22:02:57 -05:00 |
|
bssrdf
|
688de6d7d8
|
fixed bug now split-k is working
|
2025-11-05 13:47:38 -05:00 |
|
bssrdf
|
6f44f47113
|
added split-k mode for skinny mnk shapes
|
2025-11-05 13:04:37 -05:00 |
|
bssrdf
|
275c08d25d
|
add more sd like test cases
|
2025-11-04 15:16:31 -05:00 |
|
bssrdf
|
00a49c2fc1
|
another CI fix
|
2025-11-03 19:49:56 -05:00 |
|
bssrdf
|
8572313000
|
remove trailing blank
|
2025-11-03 19:45:22 -05:00 |
|
bssrdf
|
27881fbe7b
|
fixes for CI
|
2025-11-03 19:43:55 -05:00 |
|
bssrdf
|
fa9e415c9b
|
minor update of test case
|
2025-11-03 15:48:57 -05:00 |
|
bssrdf
|
417cfc3cc6
|
added a test case to directly compare im2col and implicit gemm
|
2025-10-31 19:57:28 -04:00 |