@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 842b0fd402
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 15, 23:30 UTC

[ci] Add more source file dependencies for some tests (#13123)

Signed-off-by: <> Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>

Kevin H. Luu committed Feb 11, 2025 at 20:38 UTC 842b0fd402574f49f8828fcff1b8dacc3bcab5fa
1 file changed +10 -2
.buildkite/test-pipeline.yaml
+10 -2
@@ -107,6 +107,10 @@ steps:
107 mirror_hardwares: [amd]
108 source_file_dependencies:
109 - vllm/
110 + - tests/entrypoints/llm
111 + - tests/entrypoints/openai
112 + - tests/entrypoints/test_chat_utils
113 + - tests/entrypoints/offline_mode
114 commands:
115 - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_lazy_outlines.py --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_generate_multiple_loras.py --ignore=entrypoints/llm/test_guided_generate.py --ignore=entrypoints/llm/test_collective_rpc.py
116 - pytest -v -s entrypoints/llm/test_lazy_outlines.py # it needs a clean process
@@ -124,9 +128,10 @@ steps:
128 source_file_dependencies:
129 - vllm/distributed/
130 - vllm/core/
127 - - tests/distributed
131 + - tests/distributed/test_utils
132 + - tests/distributed/test_pynccl
133 - tests/spec_decode/e2e/test_integration_dist_tp4
129 - - tests/compile
134 + - tests/compile/test_basic_correctness
135 - examples/offline_inference/rlhf.py
136 - examples/offline_inference/rlhf_colocate.py
137 commands:
@@ -174,6 +179,9 @@ steps:
179 - vllm/
180 - tests/engine
181 - tests/tokenization
182 + - tests/test_sequence
183 + - tests/test_config
184 + - tests/test_logger
185 commands:
186 - pytest -v -s engine test_sequence.py test_config.py test_logger.py
187 # OOM in the CI unless we run this separately