hailin
/
sglang0.4.5.post1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
sglang0.4.5.post1/python/sglang/srt/layers/quantization/configs
History
hailin 0558580343 first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
..
N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=512,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4096,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4608,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2048,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2304,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00
N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json first commit @ sglang v0.4.5.post1 2025-06-29 18:55:37 +08:00