Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-20 01:31:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

cleanup

Browse Source
This commit is contained in:
Disty0
2026-04-04 01:39:26 +03:00
parent 470a0d816e
commit b2e071dc52
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/sdnq/triton_mm.py
+1 -1
View File
@@ -117,7 +117,7 @@ def triton_mm_td_kernel(
off_k = 0
accumulator = tl.zeros((BLOCK_SIZE_M, BLOCK_SIZE_N), dtype=ACCUMULATOR_DTYPE)
for k in range(0, tl.cdiv(K, BLOCK_SIZE_K)):
for _ in range(0, K, BLOCK_SIZE_K):
a = a_desc.load([pid_m * BLOCK_SIZE_M, off_k])
b = b_desc.load([off_k, pid_n * BLOCK_SIZE_N])
accumulator = tl.dot(a, b, accumulator, out_dtype=ACCUMULATOR_DTYPE)