mirror of
https://github.com/FlashML-org/FreeToken.git
synced 2026-11-21 01:52:30 +08:00
* feat(quant)!: compress bf16 weights to df11 at load with --online-quant GLM-4.7 no longer hardwires DF11 attention and embedding; it serves them bf16 unless --online-quant df11 is passed, and FTW files converted with the old DF11 tensors must be reconverted. * fix(quant): skip layers --online-quant cannot convert instead of failing
16 lines
726 B
Python
16 lines
726 B
Python
from .base import LinearConfig, LinearKernel, LinearMethod
|
|
from . import df11, fp8_block, fp8_tensor, gguf, mxfp8, nvfp4, unquantized
|
|
from .df11 import Df11LinearMethod
|
|
from .fp8_block import Fp8BlockLinearMethod
|
|
from .fp8_tensor import Fp8TensorLinearMethod
|
|
from .mxfp8 import Mxfp8LinearMethod
|
|
from .nvfp4 import Nvfp4LinearMethod
|
|
from .unquantized import UnquantizedLinearMethod
|
|
from .gguf import GGUFLinearMethod
|
|
|
|
__all__ = [
|
|
"LinearConfig", "LinearKernel", "LinearMethod",
|
|
"UnquantizedLinearMethod", "Df11LinearMethod", "Fp8TensorLinearMethod", "Fp8BlockLinearMethod", "Mxfp8LinearMethod", "Nvfp4LinearMethod", "GGUFLinearMethod",
|
|
"df11", "fp8_block", "fp8_tensor", "gguf", "mxfp8", "nvfp4", "unquantized",
|
|
]
|