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] Test VLM embeddings (#9406)
Cyrus Leung committed
Oct 16, 2024 at 17:44 UTC
1de76a0e55639dfec7436c21d0c0291d6ed900e3
1 file changed
+2
.buildkite/test-pipeline.yaml
+2
@@ -340,10 +340,12 @@ steps:
340
source_file_dependencies:
341
- vllm/
342
- tests/models/embedding/language
343
+ - tests/models/embedding/vision_language
344
- tests/models/encoder_decoder/language
345
- tests/models/encoder_decoder/vision_language
346
commands:
347
- pytest -v -s models/embedding/language
348
+ - pytest -v -s models/embedding/vision_language
349
- pytest -v -s models/encoder_decoder/language
350
- pytest -v -s models/encoder_decoder/vision_language
351