text-generation-inference/server/text_generation_server/quant/__init__.py

5 lines
255 B
Python
Raw Normal View History

2023-05-02 17:07:33 +00:00
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