Files
Xiaoze Fan 56e7f3ae38 feat(quant)!: compress bf16 weights to df11 at load with --online-quant (#891)
* 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
2026-11-11 13:24:46 -08:00

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",
]