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