@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 1c445dca51
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, 07:00 UTC

[CI/Build] Print running script to enhance CI log readability (#10594)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Jee Jee Li committed Nov 24, 2024 at 11:57 UTC 1c445dca51a877ac6a5b7e03ecdb73e0e34d139e
1 file changed +11
.buildkite/test-pipeline.yaml
+11
@@ -52,6 +52,7 @@ steps:
52 - tests/worker
53 - tests/test_lazy_torch_compile.py
54 commands:
55 + - echo 'Running test_lazy_torch_compile.py...' # print running script to enhance CI log readability
56 - python3 test_lazy_torch_compile.py
57 - pytest -v -s mq_llm_engine # MQLLMEngine
58 - pytest -v -s async_engine # AsyncLLMEngine
@@ -182,15 +183,25 @@ steps:
183 - examples/
184 commands:
185 - pip install awscli tensorizer # for llava example and tensorizer test
186 + - echo 'Running offline_inference.py...' # print running script to enhance CI log readability
187 - python3 offline_inference.py
188 + - echo 'Running cpu_offload.py...'
189 - python3 cpu_offload.py
190 + - echo 'Running offline_inference_chat.py...'
191 - python3 offline_inference_chat.py
192 + - echo 'Running offline_inference_with_prefix.py...'
193 - python3 offline_inference_with_prefix.py
194 + - echo 'Running llm_engine_example.py...'
195 - python3 llm_engine_example.py
196 + - echo 'Running offline_inference_vision_language.py...'
197 - python3 offline_inference_vision_language.py
198 + - echo 'Running offline_inference_vision_language_multi_image.py...'
199 - python3 offline_inference_vision_language_multi_image.py
200 + - echo 'Running tensorize_vllm_model.py...'
201 - python3 tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors
202 + - echo 'Running offline_inference_encoder_decoder.py...'
203 - python3 offline_inference_encoder_decoder.py
204 + - echo 'Running offline_profile.py...'
205 - python3 offline_profile.py --model facebook/opt-125m
206
207 - label: Prefix Caching Test # 9min