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] Mark LoRA test as soft-fail (#8160)
Signed-off-by: kevin <kevin@anyscale.com>
Kevin H. Luu committed
Sep 4, 2024 at 20:33 UTC
ba262c4e5aa9fa753c8cedfaea5c42941184a0db
1 file changed
+1
.buildkite/test-pipeline.yaml
+1
@@ -368,6 +368,7 @@ steps:
368
- label: LoRA Long Context (Distributed) # 11min
369
# This test runs llama 13B, so it is required to run on 4 GPUs.
370
num_gpus: 4
371
+ soft_fail: true
372
source_file_dependencies:
373
- vllm/lora
374
- tests/lora/test_long_context