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 11, 20:00 UTC
[CPU][CI] Enable fused MoE tests in Arm CI (#30132)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Fadi Arafeh committed
Dec 9, 2025 at 04:55 UTC
e130845984b77b248436bdbe8f3afdf7b3107a62
1 file changed
+2
-1
.buildkite/scripts/hardware_ci/run-cpu-test-arm.sh
+2
-1
@@ -40,7 +40,8 @@ function cpu_tests() {
40
docker exec cpu-test bash -c "
41
set -e
42
pytest -x -v -s tests/kernels/test_onednn.py
43
- pytest -x -v -s tests/kernels/attention/test_cpu_attn.py"
43
+ pytest -x -v -s tests/kernels/attention/test_cpu_attn.py
44
+ pytest -x -v -s tests/kernels/moe/test_moe.py -k test_cpu_fused_moe_basic"
45
46
# basic online serving
47
docker exec cpu-test bash -c '