@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / c7c9851036
Fork 0

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):