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 9, 16:00 UTC
[CPU Backend][BugFix] Fix failing Darwin pipelines (#33002)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Fadi Arafeh committed
Jan 24, 2026 at 17:02 UTC
17ab54de81521fa3a3f2485c3897750b8ace6dc9
1 file changed
+2
-1
.github/workflows/macos-smoke-test.yml
+2
-1
@@ -29,8 +29,9 @@ jobs:
29
30
- name: Install dependencies and build vLLM
31
run: |
32
+ uv pip install -r requirements/cpu-build.txt --index-strategy unsafe-best-match
33
uv pip install -r requirements/cpu.txt --index-strategy unsafe-best-match
33
- uv pip install -e .
34
+ uv pip install -e . --no-build-isolation
35
env:
36
CMAKE_BUILD_PARALLEL_LEVEL: 4
37