diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json b/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json deleted file mode 100644 index 453d04c6a..000000000 --- a/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +++ /dev/null @@ -1,146 +0,0 @@ -{ - "1": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 1, - "num_warps": 4, - "num_stages": 4 - }, - "2": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 16, - "num_warps": 4, - "num_stages": 4 - }, - "4": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 32, - "num_warps": 4, - "num_stages": 4 - }, - "8": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 64, - "num_warps": 4, - "num_stages": 4 - }, - "16": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 1, - "num_warps": 4, - "num_stages": 3 - }, - "24": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 1, - "num_warps": 4, - "num_stages": 4 - }, - "32": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 1, - "num_warps": 4, - "num_stages": 5 - }, - "48": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 32, - "num_warps": 4, - "num_stages": 4 - }, - "64": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 64, - "num_warps": 4, - "num_stages": 4 - }, - "96": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 16, - "num_warps": 4, - "num_stages": 3 - }, - "128": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 32, - "num_warps": 4, - "num_stages": 3 - }, - "256": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 16, - "num_warps": 4, - "num_stages": 3 - }, - "512": { - "BLOCK_SIZE_M": 64, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 32, - "num_warps": 4, - "num_stages": 4 - }, - "1024": { - "BLOCK_SIZE_M": 64, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 16, - "num_warps": 4, - "num_stages": 4 - }, - "1536": { - "BLOCK_SIZE_M": 64, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 32, - "num_warps": 4, - "num_stages": 4 - }, - "2048": { - "BLOCK_SIZE_M": 64, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 32, - "num_warps": 4, - "num_stages": 4 - }, - "3072": { - "BLOCK_SIZE_M": 64, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 16, - "num_warps": 4, - "num_stages": 4 - }, - "4096": { - "BLOCK_SIZE_M": 64, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 16, - "num_warps": 4, - "num_stages": 4 - } -}