From bf21481ddef2fa9bb96c13ba1f80072abdae3eb7 Mon Sep 17 00:00:00 2001 From: Divakar Verma <137818590+divakar-amd@users.noreply.github.com> Date: Fri, 24 Jan 2025 22:17:19 -0600 Subject: [PATCH] [ROCm][MoE] MI300 tuned configs Mixtral-8x(7B,22B) | fp16, fp8 (#12408) Signed-off-by: Divakar Verma --- ...me=AMD_Instinct_MI300X,dtype=fp8_w8a8.json | 164 ++++++++++++++ ...14336,device_name=AMD_Instinct_MI300X.json | 90 ++++---- ...me=AMD_Instinct_MI300X,dtype=fp8_w8a8.json | 164 ++++++++++++++ ...16384,device_name=AMD_Instinct_MI300X.json | 200 ++++++++++++++++++ ...me=AMD_Instinct_MI300X,dtype=fp8_w8a8.json | 164 ++++++++++++++ ...=1792,device_name=AMD_Instinct_MI300X.json | 112 +++++----- ...me=AMD_Instinct_MI300X,dtype=fp8_w8a8.json | 164 ++++++++++++++ ...=2048,device_name=AMD_Instinct_MI300X.json | 200 ++++++++++++++++++ ...me=AMD_Instinct_MI300X,dtype=fp8_w8a8.json | 164 ++++++++++++++ ...=3584,device_name=AMD_Instinct_MI300X.json | 98 ++++----- ...me=AMD_Instinct_MI300X,dtype=fp8_w8a8.json | 164 ++++++++++++++ ...=4096,device_name=AMD_Instinct_MI300X.json | 200 ++++++++++++++++++ ...me=AMD_Instinct_MI300X,dtype=fp8_w8a8.json | 164 ++++++++++++++ ...=7168,device_name=AMD_Instinct_MI300X.json | 96 ++++----- ...me=AMD_Instinct_MI300X,dtype=fp8_w8a8.json | 164 ++++++++++++++ ...=8192,device_name=AMD_Instinct_MI300X.json | 200 ++++++++++++++++++ 16 files changed, 2310 insertions(+), 198 deletions(-) create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json create mode 100644 vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json new file mode 100644 index 0000000000000..b6f1d01f88652 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json @@ -0,0 +1,164 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "256": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "512": { + "BLOCK_SIZE_M": 256, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4096": { + "BLOCK_SIZE_M": 256, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json index 4d4b752fa5d64..66f9106bd1be3 100644 --- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json @@ -1,21 +1,21 @@ { "1": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_N": 16, "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "2": { "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 128, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, - "num_warps": 2, + "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -23,10 +23,10 @@ }, "4": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 256, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, - "num_warps": 2, + "num_warps": 1, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -34,10 +34,10 @@ }, "8": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 256, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, - "num_warps": 1, + "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -48,7 +48,7 @@ "BLOCK_SIZE_N": 16, "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, - "num_warps": 4, + "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -56,10 +56,10 @@ }, "24": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 64, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, - "num_warps": 1, + "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -67,57 +67,57 @@ }, "32": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 128, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 4, "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, "kpack": 1 }, - "48": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 4, - "num_warps": 2, - "num_stages": 2, - "waves_per_eu": 0, - "matrix_instr_nonkdim": 16, - "kpack": 2 - }, "64": { "BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 4, - "num_warps": 8, - "num_stages": 2, - "waves_per_eu": 0, - "matrix_instr_nonkdim": 16, - "kpack": 2 - }, - "96": { - "BLOCK_SIZE_M": 32, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, "kpack": 2 }, - "128": { - "BLOCK_SIZE_M": 64, + "96": { + "BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 64, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 4, "num_warps": 8, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 32, "kpack": 2 }, "256": { @@ -129,7 +129,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "512": { "BLOCK_SIZE_M": 128, @@ -150,7 +150,7 @@ "num_warps": 8, "num_stages": 2, "waves_per_eu": 0, - "matrix_instr_nonkdim": 32, + "matrix_instr_nonkdim": 16, "kpack": 2 }, "1536": { @@ -184,7 +184,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "4096": { "BLOCK_SIZE_M": 128, @@ -195,6 +195,6 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 } } diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json new file mode 100644 index 0000000000000..0e5fd1eec77d7 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json @@ -0,0 +1,164 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "512": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4096": { + "BLOCK_SIZE_M": 256, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json new file mode 100644 index 0000000000000..d6ad63509f157 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json @@ -0,0 +1,200 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 1, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "48": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "256": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "512": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 16, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "4096": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 16, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json new file mode 100644 index 0000000000000..8323f512db015 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json @@ -0,0 +1,164 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "256": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1536": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4096": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json index a218fc40642c1..1b46cb5716514 100644 --- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json @@ -1,10 +1,10 @@ { "1": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 256, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, - "num_warps": 2, + "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -19,9 +19,31 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "16": { "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, @@ -32,78 +54,56 @@ "matrix_instr_nonkdim": 16, "kpack": 2 }, - "8": { + "24": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 256, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, - "num_warps": 2, + "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, "kpack": 2 }, - "16": { - "BLOCK_SIZE_M": 64, - "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 64, - "GROUP_SIZE_M": 1, - "num_warps": 8, - "num_stages": 2, - "waves_per_eu": 0, - "matrix_instr_nonkdim": 16, - "kpack": 1 - }, - "24": { + "32": { "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 64, - "GROUP_SIZE_M": 1, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, "kpack": 1 }, - "32": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 256, - "GROUP_SIZE_M": 4, - "num_warps": 2, - "num_stages": 2, - "waves_per_eu": 0, - "matrix_instr_nonkdim": 16, - "kpack": 2 - }, "48": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 64, - "GROUP_SIZE_M": 1, - "num_warps": 8, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, "kpack": 2 }, "64": { - "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 64, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, - "num_warps": 2, + "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "96": { "BLOCK_SIZE_M": 32, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 256, - "GROUP_SIZE_M": 4, - "num_warps": 4, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -112,24 +112,24 @@ "128": { "BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 64, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 4, "num_warps": 8, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "256": { - "BLOCK_SIZE_M": 128, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 64, - "GROUP_SIZE_M": 4, + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, "num_warps": 8, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "512": { "BLOCK_SIZE_M": 64, @@ -151,7 +151,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "1536": { "BLOCK_SIZE_M": 128, @@ -162,7 +162,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "2048": { "BLOCK_SIZE_M": 128, @@ -184,7 +184,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "4096": { "BLOCK_SIZE_M": 128, @@ -195,6 +195,6 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 } } diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json new file mode 100644 index 0000000000000..81bb765d30031 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json @@ -0,0 +1,164 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "64": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "128": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1024": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4096": { + "BLOCK_SIZE_M": 256, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json new file mode 100644 index 0000000000000..811c77ab41093 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json @@ -0,0 +1,200 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "16": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 32, + "kpack": 2 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "4096": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json new file mode 100644 index 0000000000000..379ca107a9469 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json @@ -0,0 +1,164 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "64": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1024": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4096": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json index 3682cc548f352..ed5b655d89937 100644 --- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json @@ -1,21 +1,21 @@ { "1": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 128, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, - "num_warps": 2, + "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "2": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, - "num_warps": 2, + "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -23,10 +23,10 @@ }, "4": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 256, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, - "num_warps": 2, + "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -34,7 +34,7 @@ }, "8": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_N": 16, "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, "num_warps": 2, @@ -52,31 +52,9 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 2 - }, - "24": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 64, - "GROUP_SIZE_M": 1, - "num_warps": 4, - "num_stages": 2, - "waves_per_eu": 0, - "matrix_instr_nonkdim": 16, "kpack": 1 }, - "32": { - "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, - "BLOCK_SIZE_K": 256, - "GROUP_SIZE_M": 4, - "num_warps": 2, - "num_stages": 2, - "waves_per_eu": 0, - "matrix_instr_nonkdim": 16, - "kpack": 2 - }, - "48": { + "24": { "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 32, "BLOCK_SIZE_K": 256, @@ -87,6 +65,28 @@ "matrix_instr_nonkdim": 16, "kpack": 2 }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "48": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, "64": { "BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 32, @@ -101,40 +101,40 @@ "96": { "BLOCK_SIZE_M": 32, "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 128, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 4, - "num_warps": 4, + "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "128": { "BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 4, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, "num_warps": 8, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "256": { - "BLOCK_SIZE_M": 128, - "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 64, - "GROUP_SIZE_M": 4, + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, "num_warps": 8, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "512": { "BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 64, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 1, "num_warps": 8, "num_stages": 2, @@ -151,7 +151,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "1536": { "BLOCK_SIZE_M": 128, @@ -173,7 +173,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "3072": { "BLOCK_SIZE_M": 128, @@ -195,6 +195,6 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 } } diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json new file mode 100644 index 0000000000000..48bb5f2ccb8e3 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json @@ -0,0 +1,164 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4096": { + "BLOCK_SIZE_M": 256, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json new file mode 100644 index 0000000000000..a64d06c6d1724 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json @@ -0,0 +1,200 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "48": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 32, + "kpack": 2 + }, + "512": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "4096": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json new file mode 100644 index 0000000000000..bd2c6fbc1b941 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json @@ -0,0 +1,164 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "16": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "24": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "32": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "48": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "96": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "256": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4096": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json index 21742854c613f..822f04e33e879 100644 --- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json @@ -1,7 +1,7 @@ { "1": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_N": 32, "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, "num_warps": 2, @@ -12,54 +12,54 @@ }, "2": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 32, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, - "num_warps": 4, + "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "4": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 128, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, - "num_warps": 4, + "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "8": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_N": 16, "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, + "num_warps": 1, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, "kpack": 1 }, - "16": { + "24": { "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 16, "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 1, - "num_warps": 4, - "num_stages": 2, - "waves_per_eu": 0, - "matrix_instr_nonkdim": 16, - "kpack": 2 - }, - "24": { - "BLOCK_SIZE_M": 32, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 1, - "num_warps": 8, + "num_warps": 1, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, @@ -68,7 +68,7 @@ "32": { "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 128, + "BLOCK_SIZE_K": 256, "GROUP_SIZE_M": 4, "num_warps": 2, "num_stages": 2, @@ -78,52 +78,52 @@ }, "48": { "BLOCK_SIZE_M": 16, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 4, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, "num_warps": 2, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 - }, - "64": { - "BLOCK_SIZE_M": 32, - "BLOCK_SIZE_N": 32, - "BLOCK_SIZE_K": 128, - "GROUP_SIZE_M": 4, - "num_warps": 4, - "num_stages": 2, - "waves_per_eu": 0, - "matrix_instr_nonkdim": 16, "kpack": 2 }, - "96": { + "64": { "BLOCK_SIZE_M": 32, - "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_N": 64, "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 4, "num_warps": 4, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, "kpack": 2 }, "128": { "BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 64, - "BLOCK_SIZE_K": 64, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 4, "num_warps": 8, "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "256": { "BLOCK_SIZE_M": 128, "BLOCK_SIZE_N": 128, - "BLOCK_SIZE_K": 64, + "BLOCK_SIZE_K": 128, "GROUP_SIZE_M": 4, "num_warps": 8, "num_stages": 2, @@ -140,7 +140,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "1024": { "BLOCK_SIZE_M": 128, @@ -151,7 +151,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "1536": { "BLOCK_SIZE_M": 128, @@ -173,7 +173,7 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 }, "3072": { "BLOCK_SIZE_M": 128, @@ -187,7 +187,7 @@ "kpack": 2 }, "4096": { - "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_M": 256, "BLOCK_SIZE_N": 128, "BLOCK_SIZE_K": 64, "GROUP_SIZE_M": 1, @@ -195,6 +195,6 @@ "num_stages": 2, "waves_per_eu": 0, "matrix_instr_nonkdim": 16, - "kpack": 1 + "kpack": 2 } } diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json new file mode 100644 index 0000000000000..cd4fb8f11b935 --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json @@ -0,0 +1,164 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 1, + "num_stages": 2, + "waves_per_eu": 0 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "48": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 1, + "num_stages": 2, + "waves_per_eu": 0 + }, + "96": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0 + }, + "512": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + }, + "4096": { + "BLOCK_SIZE_M": 256, + "BLOCK_SIZE_N": 256, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0 + } +} diff --git a/vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json b/vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json new file mode 100644 index 0000000000000..cf66868e9d57a --- /dev/null +++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json @@ -0,0 +1,200 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 1, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 16, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 1, + "num_warps": 1, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 1 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "24": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 1, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 128, + "GROUP_SIZE_M": 4, + "num_warps": 2, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "48": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "64": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "96": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 256, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 4, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "256": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 4, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "512": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "1536": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "3072": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + }, + "4096": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 64, + "GROUP_SIZE_M": 1, + "num_warps": 8, + "num_stages": 2, + "waves_per_eu": 0, + "matrix_instr_nonkdim": 16, + "kpack": 2 + } +}