@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / eda2b3589c
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

Revert "Print running script to enhance CI log readability" (#10601)

youkaichao committed Nov 23, 2024 at 21:31 UTC eda2b3589c8b27a9b8f8aea24afe1673890d19d2
1 file changed -11
.buildkite/test-pipeline.yaml
-11
@@ -52,7 +52,6 @@ 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
55 - python3 test_lazy_torch_compile.py
56 - pytest -v -s mq_llm_engine # MQLLMEngine
57 - pytest -v -s async_engine # AsyncLLMEngine
@@ -183,25 +182,15 @@ steps:
182 - examples/
183 commands:
184 - pip install awscli tensorizer # for llava example and tensorizer test
186 - - echo 'Running offline_inference.py...' # print running script to enhance CI log readability
185 - python3 offline_inference.py
188 - - echo 'Running cpu_offload.py...'
186 - python3 cpu_offload.py
190 - - echo 'Running offline_inference_chat.py...'
187 - python3 offline_inference_chat.py
192 - - echo 'Running offline_inference_with_prefix.py...'
188 - python3 offline_inference_with_prefix.py
194 - - echo 'Running llm_engine_example.py...'
189 - python3 llm_engine_example.py
196 - - echo 'Running offline_inference_vision_language.py...'
190 - python3 offline_inference_vision_language.py
198 - - echo 'Running offline_inference_vision_language_multi_image.py...'
191 - python3 offline_inference_vision_language_multi_image.py
200 - - echo 'Running tensorize_vllm_model.py...'
192 - 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...'
193 - python3 offline_inference_encoder_decoder.py
204 - - echo 'Running offline_profile.py...'
194 - python3 offline_profile.py --model facebook/opt-125m
195
196 - label: Prefix Caching Test # 9min