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
DecodingParams -> SamplingParams
Woosuk Kwon committed
Feb 23, 2023 at 07:38 UTC
86c682cd32efe8a3322ab47ed0d7bed06809f43d
1 file changed
+1
-1
cacheflow/decoding.py
+1
-1
@@ -1,7 +1,7 @@
1
from typing import Optional, Set
2
3
4
-class DecodingParams:
4
+class SamplingParams:
5
6
def __init__(
7
self,