Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-17 16:24:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

reduce num_stages options in triton atten

Browse Source
This commit is contained in:
Disty0
2026-07-14 23:48:55 +03:00
parent 39d74cca18
commit d03d0d7dd1
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/sdnq/kernels/triton_atten.py
+1 -1
View File
@@ -15,7 +15,7 @@ matmul_configs = [
for BM in [int(BM) for BM in os.environ.get("SDNQ_TRITON_ATTEN_BLOCK_SIZE_M_LIST", "64,128").replace(" ","").split(",")]
for BN in [int(BN) for BN in os.environ.get("SDNQ_TRITON_ATTEN_BLOCK_SIZE_N_LIST", "32,64").replace(" ","").split(",")]
for w in [int(w) for w in os.environ.get("SDNQ_TRITON_ATTEN_NUM_WARPS_LIST", "4,8").replace(" ","").split(",")]
for s in [int(s) for s in os.environ.get("SDNQ_TRITON_ATTEN_NUM_STAGES_LIST", "1,2,4").replace(" ","").split(",")]
for s in [int(s) for s in os.environ.get("SDNQ_TRITON_ATTEN_NUM_STAGES_LIST", "1,2" if (torch.cuda.is_available() and torch.version.hip) else "2,4").replace(" ","").split(",")]
]