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, 17:00 UTC
[CI/Build] Excluding test_moe.py from AMD Kernels tests for investigation (#8373)
Alexey Kondratiev(AMD) committed
Sep 11, 2024 at 14:31 UTC
aea02f30def76b188112b553fbd89e47829f6327
1 file changed
+1
.buildkite/run-amd-test.sh
+1
@@ -87,6 +87,7 @@ if [[ $commands == *" kernels "* ]]; then
87
--ignore=kernels/test_machete_gemm.py \
88
--ignore=kernels/test_mamba_ssm.py \
89
--ignore=kernels/test_marlin_gemm.py \
90
+ --ignore=kernels/test_moe.py \
91
--ignore=kernels/test_prefix_prefill.py \
92
--ignore=kernels/test_rand.py \
93
--ignore=kernels/test_sampler.py"