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 15, 21:00 UTC
[ROCm] Disable a few more kernel tests that are broken on ROCm (#14145)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Sage Moore committed
Mar 4, 2025 at 15:37 UTC
3e1d223626499a75edfd3f2ed463197e2c7b387b
1 file changed
+6
-1
.buildkite/run-amd-test.sh
+6
-1
@@ -93,7 +93,12 @@ if [[ $commands == *" kernels "* ]]; then
93
--ignore=kernels/test_rand.py \
94
--ignore=kernels/test_sampler.py \
95
--ignore=kernels/test_cascade_flash_attn.py \
96
- --ignore=kernels/test_mamba_mixer2.py"
96
+ --ignore=kernels/test_mamba_mixer2.py \
97
+ --ignore=kernels/test_aqlm.py \
98
+ --ignore=kernels/test_machete_mm.py \
99
+ --ignore=kernels/test_mha_attn.py \
100
+ --ignore=kernels/test_block_fp8.py \
101
+ --ignore=kernels/test_permute_cols.py"
102
fi
103
104
#ignore certain Entrypoints tests