Directory listing for /agent-env/lib/python3.11/site-packages/vllm/model_executor/layers/quantization/utils/configs/
- N=10240,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json
- N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=5120,K=25600,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json
- N=5120,K=8192,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json
- N=51200,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
- N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
- N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json
- N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
- README.md