mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-23 16:02:10 +00:00
5 lines
255 B
Python
5 lines
255 B
Python
from .quantizer import Quantizer
|
|
from .fused_attn import QuantLlamaAttention, make_quant_attn
|
|
from .fused_mlp import QuantLlamaMLP, make_fused_mlp, autotune_warmup_fused
|
|
from .quant_linear import QuantLinear, make_quant_linear, autotune_warmup_linear
|