Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-18 16:54:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

AMD takes forever to compile with num_stages > 1

Browse Source
This commit is contained in:
Dity0
2026-08-06 15:20:14 +03:00
parent 5d71061946
commit 08b2729c22
3 changed files with 3 additions and 3 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", "8,16" if torch.xpu.is_available() else "4,8").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").replace(" ","").split(",")]
for s in [int(s) for s in os.environ.get("SDNQ_TRITON_ATTEN_NUM_STAGES_LIST", "1" if (torch.cuda.is_available() and torch.version.hip) else "2").replace(" ","").split(",")]
]
modules/sdnq/kernels/triton_mm.py
+1 -1
View File
@@ -14,7 +14,7 @@ matmul_configs = [
for BK in [int(BK) for BK in os.environ.get("SDNQ_TRITON_MM_BLOCK_SIZE_K_LIST", "32,64,128").replace(" ","").split(",")]
for GM in [int(GM) for GM in os.environ.get("SDNQ_TRITON_MM_GROUP_SIZE_M_LIST", "8").replace(" ","").split(",")]
for w in [int(w) for w in os.environ.get("SDNQ_TRITON_MM_NUM_WARPS_LIST", "16" if torch.xpu.is_available() else "4").replace(" ","").split(",")]
for s in [int(s) for s in os.environ.get("SDNQ_TRITON_MM_NUM_STAGES_LIST", "1,2" if (torch.cuda.is_available() and torch.version.hip) else "2").replace(" ","").split(",")]
for s in [int(s) for s in os.environ.get("SDNQ_TRITON_MM_NUM_STAGES_LIST", "1" if (torch.cuda.is_available() and torch.version.hip) else "2").replace(" ","").split(",")]
]
modules/sdnq/kernels/triton_scaled_mm.py
+1 -1
View File
@@ -14,7 +14,7 @@ matmul_configs = [
for BK in [int(BK) for BK in os.environ.get("SDNQ_TRITON_MM_BLOCK_SIZE_K_LIST", "32,64,128").replace(" ","").split(",")]
for GM in [int(GM) for GM in os.environ.get("SDNQ_TRITON_MM_GROUP_SIZE_M_LIST", "8").replace(" ","").split(",")]
for w in [int(w) for w in os.environ.get("SDNQ_TRITON_MM_NUM_WARPS_LIST", "16" if torch.xpu.is_available() else "4").replace(" ","").split(",")]
for s in [int(s) for s in os.environ.get("SDNQ_TRITON_MM_NUM_STAGES_LIST", "1,2" if (torch.cuda.is_available() and torch.version.hip) else "2").replace(" ","").split(",")]
for s in [int(s) for s in os.environ.get("SDNQ_TRITON_MM_NUM_STAGES_LIST", "1" if (torch.cuda.is_available() and torch.version.hip) else "2").replace(" ","").split(",")]
]