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,