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, 07:00 UTC
[CI][Installation] Avoid uploading CUDA 11.8 wheel (#10535)
Signed-off-by: simon-mo <simon.mo@hey.com> Co-authored-by: simon-mo <simon.mo@hey.com>
Yunmeng committed
Nov 22, 2024 at 05:03 UTC
edec3385b641afb22739a6ec0fd0145f8f1141c5
1 file changed
+6
-1
.buildkite/upload-wheels.sh
+6
-1
@@ -25,7 +25,12 @@ echo "Version: $version"
25
26
# If the version contains "dev", rename it to v1.0.0.dev for consistency
27
if [[ $version == *dev* ]]; then
28
- new_version="1.0.0.dev"
28
+ suffix="${version##*.}"
29
+ if [[ $suffix == cu* ]]; then
30
+ new_version="1.0.0.dev+${suffix}"
31
+ else
32
+ new_version="1.0.0.dev"
33
+ fi
34
new_wheel="${wheel/$version/$new_version}"
35
mv -- "$wheel" "$new_wheel"
36
wheel="$new_wheel"