chatlawv1 / tools /quant /__init__.py
teachyourselfcoding's picture
Upload 245 files
fa6856c
raw
history blame
No virus
251 Bytes
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