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, 00:30 UTC
[CI/Build] increase wheel size limit to 200 MB (#5130)
youkaichao committed
May 30, 2024 at 06:29 UTC
f758505c736ce53a13567852594c3e05215bb6b2
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 = 150
4
+MAX_SIZE_MB = 200
5
6
7
def print_top_10_largest_files(zip_file):