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, 05:45 UTC
[Bugfix] Fix test-pipeline.yaml (#10973)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Dec 7, 2024 at 12:08 UTC
acf092d34802b187f27daa8e1626f67552bde193
1 file changed
+1
-1
.buildkite/test-pipeline.yaml
+1
-1
@@ -237,7 +237,7 @@ steps:
237
source_file_dependencies:
238
- vllm/lora
239
- tests/lora
240
- command: pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore lora/test_long_context.py lora/test_chatglm3_tp.py lora/test_llama_tp.py
240
+ command: pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_long_context.py --ignore=lora/test_chatglm3_tp.py --ignore=lora/test_llama_tp.py
241
parallelism: 4
242
243
- label: "PyTorch Fullgraph Smoke Test" # 9min