RedHatAI
/

moe

Model card Files Files and versions

moe / torch-ext /moe

484 kB

Ctrl+K

Ctrl+K

4 contributors

History: 2 commits

danieldk's picture

danieldk HF Staff

Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8`

b41d28a over 1 year ago

configs
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago
utils
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago
__init__.py

2.4 kB
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago
fp8.py

2.45 kB
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago
fp8_utils.py

12.2 kB
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago
fused_marlin_moe.py

12.9 kB
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago
fused_moe.py

48.3 kB
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago
platforms.py

1.77 kB
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago
scalar_type.py

11.8 kB
Vendor `w8a8_block_fp8_matmul` and `per_token_group_quant_fp8` over 1 year ago