Skip to content

GitLab

Unverified Commit cadd5dbe authored by Wen-Heng (Jack) Chung's avatar Wen-Heng (Jack) Chung Committed by GitHub
Browse files

Tune MI300X fused MoE Triton kernel JSON config. (#3492)

parent bb418ced
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
python/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
View file @ cadd5dbe
...@@ -72,10 +72,10 @@ ...@@ -72,10 +72,10 @@
"waves_per_eu": 0 "waves_per_eu": 0
}, },
"64": { "64": {
"BLOCK_SIZE_M": 256, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128, "BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 4,
"num_warps": 4, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0 "waves_per_eu": 0
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment