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 14, 05:30 UTC
[CI] Block the cu126 wheel build while broken (#23285)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Aug 21, 2025 at 00:21 UTC
f64ee61d9e7014a5f230a8347186b952dbe483de
1 file changed
+5
.buildkite/release-pipeline.yaml
+5
@@ -27,7 +27,12 @@ steps:
27
env:
28
DOCKER_BUILDKIT: "1"
29
30
+ - block: "Build CUDA 12.6 wheel"
31
+ key: block-build-cu126-wheel
32
+ depends_on: ~
33
+
34
- label: "Build wheel - CUDA 12.6"
35
+ depends_on: block-build-cu126-wheel
36
id: build-wheel-cuda-12-6
37
agents:
38
queue: cpu_queue_postmerge