@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / edec3385b6
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, 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"