@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 608f74ffe5
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 17, 09:15 UTC

Minor

Woosuk Kwon committed Feb 22, 2023 at 18:08 UTC 608f74ffe5635cd8ac7fc78a13e3d67a4f59b9e0
1 file changed +1 -1
cacheflow/models/model_utils.py
+1 -1
@@ -1,6 +1,6 @@
1 import torch.nn as nn
2
3 -from cacheflow.worker.models.opt import OPTForCausalLM
3 +from cacheflow.models.opt import OPTForCausalLM
4
5 MODEL_CLASSES = {
6 'opt': OPTForCausalLM,