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, 10:45 UTC
[ci/build] Add placeholder command for custom models test (#9262)
Kevin H. Luu committed
Oct 10, 2024 at 15:45 UTC
a78c6ba7c88a7bb42b38410f9dcfa5b342b95b57
1 file changed
+2
-1
.buildkite/test-pipeline.yaml
+2
-1
@@ -347,10 +347,11 @@ steps:
347
- pytest -v -s models/encoder_decoder/language
348
- pytest -v -s models/encoder_decoder/vision_language
349
350
+# This test is used only in PR development phase to test individual models and should never run on main
351
- label: Custom Models Test
351
- #mirror_hardwares: [amd]
352
optional: true
353
commands:
354
+ - echo 'Testing custom models...'
355
# PR authors can temporarily add commands below to test individual models
356
# e.g. pytest -v -s models/encoder_decoder/vision_language/test_mllama.py
357
# *To avoid merge conflicts, remember to REMOVE (not just comment out) them before merging the PR*