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
12 lines
425 B
Python
12 lines
425 B
Python
from .base import EmbeddingConfig, EmbeddingKernel, EmbeddingMethod
|
|
from . import df11, gguf, unquantized
|
|
from .df11 import Df11EmbeddingMethod
|
|
from .gguf import GGUFEmbeddingMethod
|
|
from .unquantized import UnquantizedEmbeddingMethod
|
|
|
|
__all__ = [
|
|
"EmbeddingConfig", "EmbeddingKernel", "EmbeddingMethod",
|
|
"UnquantizedEmbeddingMethod", "Df11EmbeddingMethod", "GGUFEmbeddingMethod",
|
|
"df11", "gguf", "unquantized",
|
|
]
|