Skip to content

Commit d4de040

Browse files
shihaobaishihaobai
committed
merge main
2 parents 0ef48cb + f4193c6 commit d4de040

File tree

117 files changed

+1892
-589
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

117 files changed

+1892
-589
lines changed

‎lightllm/common/all_kernel_configs/deepseek_v3_rotary_emb_kernel/{HEAD_DIM=64,K_HEAD_NUM=1,Q_HEAD_NUM=128,dtype=torch.bfloat16}_NVIDIA_H200.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"8192": {"BLOCK_SEQ": 1, "HEAD_PARALLEL_NUM": 4, "num_warps": 1, "num_stages": 5}}

‎lightllm/common/all_kernel_configs/deepseek_v3_rotary_emb_kernel/{HEAD_DIM=64,K_HEAD_NUM=1,Q_HEAD_NUM=16,dtype=torch.bfloat16}_NVIDIA_H200.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"8192": {"BLOCK_SEQ": 1, "HEAD_PARALLEL_NUM": 2, "num_warps": 1, "num_stages": 1}}

‎lightllm/common/all_kernel_configs/deepseek_v3_rotary_emb_kernel/{HEAD_DIM=64,K_HEAD_NUM=1,Q_HEAD_NUM=32,dtype=torch.bfloat16}_NVIDIA_H200.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"8192": {"BLOCK_SEQ": 1, "HEAD_PARALLEL_NUM": 2, "num_warps": 1, "num_stages": 1}}

‎lightllm/common/all_kernel_configs/deepseek_v3_rotary_emb_kernel/{HEAD_DIM=64,K_HEAD_NUM=1,Q_HEAD_NUM=64,dtype=torch.bfloat16}_NVIDIA_H200.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"8192": {"BLOCK_SEQ": 1, "HEAD_PARALLEL_NUM": 4, "num_warps": 1, "num_stages": 1}}

‎lightllm/common/all_kernel_configs/deepseek_v3_rotary_emb_kernel/{HEAD_DIM=64,K_HEAD_NUM=1,Q_HEAD_NUM=8,dtype=torch.bfloat16}_NVIDIA_H200.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"8192": {"BLOCK_SEQ": 1, "HEAD_PARALLEL_NUM": 1, "num_warps": 1, "num_stages": 5}}

‎lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=128,N=7168,expert_num=256,mul_routed_weight=true,out_dtype=torch.bfloat16,topk_num=1,use_fp8_w8a8=true}_NVIDIA_H100_80GB_HBM3.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"1": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 32, "GROUP_SIZE_M": 4, "num_warps": 2, "num_stages": 3}, "8": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 2}, "64": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 4}, "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": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "1024": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "4096": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "8192": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}}

‎lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=128,N=7168,expert_num=256,mul_routed_weight=true,out_dtype=torch.bfloat16,topk_num=1,use_fp8_w8a8=true}_NVIDIA_H200.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"1": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 32, "GROUP_SIZE_M": 2, "num_warps": 2, "num_stages": 3}, "8": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 2}, "64": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "128": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "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": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "1024": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "4096": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "8192": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}}

‎lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=192,N=4096,expert_num=128,mul_routed_weight=true,out_dtype=torch.bfloat16,topk_num=1,use_fp8_w8a8=false}_NVIDIA_H100_80GB_HBM3.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"1": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 32, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "8": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 2}, "64": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 3}, "128": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 3}, "256": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "512": {"BLOCK_SIZE_M": 64, "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": 4, "num_warps": 4, "num_stages": 3}, "4096": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 32, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 4}, "8192": {"BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "16384": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "32768": {"BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}}

‎lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=192,N=4096,expert_num=128,mul_routed_weight=true,out_dtype=torch.bfloat16,topk_num=1,use_fp8_w8a8=true}_NVIDIA_H100_80GB_HBM3.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"1": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 2, "num_stages": 1}, "8": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 1}, "64": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 8, "num_stages": 4}, "256": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 4}, "512": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 4}, "1024": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "4096": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 8, "num_stages": 4}, "8192": {"BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 8, "num_stages": 4}}

‎lightllm/common/all_kernel_configs/grouped_moe_gemm_kernel/{K=256,N=7168,expert_num=256,mul_routed_weight=true,out_dtype=torch.bfloat16,topk_num=1,use_fp8_w8a8=true}_NVIDIA_H100_80GB_HBM3.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"1": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 32, "GROUP_SIZE_M": 4, "num_warps": 2, "num_stages": 3}, "8": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 2}, "64": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 2}, "128": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 2, "num_warps": 4, "num_stages": 2}, "256": {"BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, "num_warps": 4, "num_stages": 3}, "512": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 4}, "1024": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "4096": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}, "8192": {"BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 3}}

0 commit comments

Comments
 (0)