From 74d03143e27a94736cfe1ff4ede07d8a73f5b545 Mon Sep 17 00:00:00 2001 From: "minke.yu" Date: Mon, 19 Oct 2026 10:13:59 +0800 Subject: [PATCH] PR #41098: H20 block-FP8 tuned GEMM configs Source: https://github.com/sgl-project/sglang/pull/41098 (applied via GitHub .diff, 3way) --- ...e,dtype=fp8_w8a8,block_shape=[32, 32].json | 134 +++++++++++++++++ ...e,dtype=fp8_w8a8,block_shape=[32, 32].json | 128 ++++++++++++++++ ...e,dtype=fp8_w8a8,block_shape=[32, 32].json | 128 ++++++++++++++++ ...e,dtype=fp8_w8a8,block_shape=[32, 32].json | 126 ++++++++++++++++ ...e,dtype=fp8_w8a8,block_shape=[32, 32].json | 122 ++++++++++++++++ ...e,dtype=fp8_w8a8,block_shape=[32, 32].json | 138 ++++++++++++++++++ 6 files changed, 776 insertions(+) create mode 100644 python/sglang/kernels/ops/quantization/configs/N=1792,K=5120,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json create mode 100644 python/sglang/kernels/ops/quantization/configs/N=25600,K=6144,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json create mode 100644 python/sglang/kernels/ops/quantization/configs/N=4096,K=1280,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json create mode 100644 python/sglang/kernels/ops/quantization/configs/N=5120,K=1024,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json create mode 100644 python/sglang/kernels/ops/quantization/configs/N=5120,K=288,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json create mode 100644 python/sglang/kernels/ops/quantization/configs/N=576,K=5120,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json diff --git a/python/sglang/kernels/ops/quantization/configs/N=1792,K=5120,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json b/python/sglang/kernels/ops/quantization/configs/N=1792,K=5120,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json new file mode 100644 index 0000000000..ef49380a6e --- /dev/null +++ b/python/sglang/kernels/ops/quantization/configs/N=1792,K=5120,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json @@ -0,0 +1,134 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 8 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 8 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 8 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 8 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 8 + }, + "32": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 8 + }, + "64": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 8 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 4 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 4 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 2 + }, + "1024": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "2048": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "4096": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "8192": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4 + } +} diff --git a/python/sglang/kernels/ops/quantization/configs/N=25600,K=6144,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json b/python/sglang/kernels/ops/quantization/configs/N=25600,K=6144,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json new file mode 100644 index 0000000000..5db0cd1bc4 --- /dev/null +++ b/python/sglang/kernels/ops/quantization/configs/N=25600,K=6144,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json @@ -0,0 +1,128 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "32": { + "BLOCK_SIZE_M": 32, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 4 + }, + "64": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 2 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "1024": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "2048": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "4096": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "8192": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + } +} diff --git a/python/sglang/kernels/ops/quantization/configs/N=4096,K=1280,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json b/python/sglang/kernels/ops/quantization/configs/N=4096,K=1280,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json new file mode 100644 index 0000000000..dddbb88774 --- /dev/null +++ b/python/sglang/kernels/ops/quantization/configs/N=4096,K=1280,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json @@ -0,0 +1,128 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 2 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 1 + }, + "64": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 2 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "1024": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "2048": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "4096": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "8192": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + } +} diff --git a/python/sglang/kernels/ops/quantization/configs/N=5120,K=1024,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json b/python/sglang/kernels/ops/quantization/configs/N=5120,K=1024,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json new file mode 100644 index 0000000000..e05c17ccc2 --- /dev/null +++ b/python/sglang/kernels/ops/quantization/configs/N=5120,K=1024,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json @@ -0,0 +1,126 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 4 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 1 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 1 + }, + "64": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4 + }, + "1024": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "2048": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4 + }, + "4096": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "8192": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + } +} diff --git a/python/sglang/kernels/ops/quantization/configs/N=5120,K=288,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json b/python/sglang/kernels/ops/quantization/configs/N=5120,K=288,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json new file mode 100644 index 0000000000..484bd0de8c --- /dev/null +++ b/python/sglang/kernels/ops/quantization/configs/N=5120,K=288,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json @@ -0,0 +1,122 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 1 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 1 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 1 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 1 + }, + "64": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 32, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "512": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "1024": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "2048": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "4096": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "8192": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + } +} diff --git a/python/sglang/kernels/ops/quantization/configs/N=576,K=5120,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json b/python/sglang/kernels/ops/quantization/configs/N=576,K=5120,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json new file mode 100644 index 0000000000..583e274c21 --- /dev/null +++ b/python/sglang/kernels/ops/quantization/configs/N=576,K=5120,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[32, 32].json @@ -0,0 +1,138 @@ +{ + "1": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 16 + }, + "2": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 16 + }, + "4": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 16 + }, + "8": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 16 + }, + "16": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 16 + }, + "32": { + "BLOCK_SIZE_M": 16, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 4, + "SWAP_AB": true, + "SPLIT_K": 8 + }, + "64": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 16 + }, + "128": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 4 + }, + "256": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 4 + }, + "512": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 4 + }, + "1024": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 2 + }, + "2048": { + "BLOCK_SIZE_M": 128, + "BLOCK_SIZE_N": 64, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + }, + "4096": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3, + "SWAP_AB": false, + "SPLIT_K": 2 + }, + "8192": { + "BLOCK_SIZE_M": 64, + "BLOCK_SIZE_N": 128, + "BLOCK_SIZE_K": 32, + "GROUP_SIZE_M": 32, + "num_warps": 4, + "num_stages": 3 + } +}