EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[ROCm] Add ROCm tuning config to block gemm and Re-tune for AMD Radeon Graphics (#3418)

Browse Source 
Co-authored-by: Bruce Xue <yigex@xilinx.com>
Co-authored-by: HAI <hixiao@gmail.com>
This commit is contained in:
yigex
2025-02-11 15:55:04 +08:00
committed by GitHub
parent 5f0e7de339
commit fdf04a1426
11 changed files with 432 additions and 385 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json
View File

@@ -72,10 +72,10 @@
"waves_per_eu": 0
},
"64": {
"BLOCK_SIZE_M": 256,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0