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, 00:45 UTC
[ci/build] fix wheel size check (#12396)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Jan 24, 2025 at 17:31 UTC
c7c98510360693be668b654c7b1c168d1e656f2c
1 file changed
+4
-2
.buildkite/check-wheel-size.py
+4
-2
@@ -2,8 +2,10 @@ import os
2
import sys
3
import zipfile
4
5
-# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 250 MB
6
-VLLM_MAX_SIZE_MB = int(os.environ.get('VLLM_MAX_SIZE_MB', 250))
5
+# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 300 MiB
6
+# Note that we have 400 MiB quota, please use it wisely.
7
+# See https://github.com/pypi/support/issues/3792 .
8
+VLLM_MAX_SIZE_MB = int(os.environ.get('VLLM_MAX_SIZE_MB', 300))
9
10
11
def print_top_10_largest_files(zip_file):