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 16, 20:45 UTC
[build] relax wheel size limit (#6704)
youkaichao committed
Jul 23, 2024 at 14:03 UTC
72fc7048032a9a12f42c76e60c0d8ca3673f0692
1 file changed
+1
-1
.buildkite/check-wheel-size.py
+1
-1
@@ -1,7 +1,7 @@
1
import os
2
import zipfile
3
4
-MAX_SIZE_MB = 200
4
+MAX_SIZE_MB = 250
5
6
7
def print_top_10_largest_files(zip_file):