Hugging Face's logo

kernels-community
/
quantization

kernel
Model card Files Community
1
quantization
File size: 679 Bytes 
165b25c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
 
from .compressed_tensors import scaled_fp8_quant, scaled_int8_quant
from .cutlass import (
    cutlass_scaled_mm_supports_fp8,
    cutlass_scaled_mm,
    cutlass_scaled_mm_azp,
)
from .marlin import (
    awq_marlin_repack,
    fp8_marlin_gemm,
    gptq_marlin_gemm,
    gptq_marlin_repack,
    gptq_marlin_24_gemm,
    marlin_qqq_gemm,
    marlin_gemm,
)

__all__ = [
    "awq_marlin_repack",
    "cutlass_scaled_mm",
    "cutlass_scaled_mm_azp",
    "cutlass_scaled_mm_supports_fp8",
    "fp8_marlin_gemm",
    "gptq_marlin_24_gemm",
    "gptq_marlin_gemm",
    "gptq_marlin_repack",
    "marlin_gemm",
    "marlin_qqq_gemm",
    "scaled_fp8_quant",
    "scaled_int8_quant",
]