add H800 grouped moe kernel configs. (#682)

Co-authored-by: wangzaijun <[email protected]>

Author: hiworldwzj

lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=192,N=5120,expert_num=160,mul_routed_weight=true,out_dtype=torch.bfloat16,topk_num=1,use_fp8_w8a8=true}_NVIDIA_H800.json

@@ -0,0 +1 @@
+{"1": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 5}, "8": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 4}, "64": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 3}, "256": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "512": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 3}, "1024": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 4}, "4096": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 4}, "8192": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 32, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 4}}

lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=2048,N=1408,expert_num=64,mul_routed_weight=false,out_dtype=torch.bfloat16,topk_num=6,use_fp8_w8a8=false}_NVIDIA_H800.json

@@ -0,0 +1 @@
+{"1": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 16, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 2, "num_stages": 5}, "8": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 32, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 2, "num_stages": 3}, "64": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 3}, "128": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "256": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 8, "num_warps": 4, "num_stages": 3}, "512": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 3}, "1024": {"BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 3}, "4096": {"BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 8, "num_warps": 4, "num_stages": 3}, "8192": {"BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 3}}

lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=5120,N=384,expert_num=160,mul_routed_weight=false,out_dtype=torch.bfloat16,topk_num=6,use_fp8_w8a8=true}_NVIDIA_H800.json

@@ -0,0 +1 @@
+{"1": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 5}, "8": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 5}, "64": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 5}, "128": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 5}, "256": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 5}, "512": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 5}, "1024": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 3}, "4096": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 3}, "8192": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 3}}

lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=704,N=2048,expert_num=64,mul_routed_weight=true,out_dtype=torch.bfloat16,topk_num=1,use_fp8_w8a8=false}_NVIDIA_H800.json

@@ -0,0 +1 @@
+{"1": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 32, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 5}, "8": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 4}, "64": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 8, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 4}, "256": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 8, "num_warps": 4, "num_stages": 4}, "512": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 4}, "1024": {"BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "4096": {"BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 8, "num_warps": 4, "num_stages": 3}, "8192": {"BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}}