@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 1de76a0e55
Fork 0

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