biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[torch.compile] avoid Dynamo guard evaluation overhead (#7898)

Browse Source 
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
youkaichao
2024-08-28 16:10:12 -07:00
committed by GitHub
parent 3cdfe1f38b
commit ce6bf3a2cf
9 changed files with 190 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/run-tpu-test.sh
View File

@@ -12,4 +12,4 @@ remove_docker_container
# For HF_TOKEN.
source /etc/environment
# Run a simple end-to-end example.
docker run --privileged --net host --shm-size=16G -it -e HF_TOKEN=$HF_TOKEN --name tpu-test vllm-tpu /bin/bash -c "python3 -m pip install git+https://github.com/thuml/depyf.git && python3 /workspace/vllm/tests/tpu/test_compilation.py && python3 /workspace/vllm/examples/offline_inference_tpu.py"
docker run --privileged --net host --shm-size=16G -it -e HF_TOKEN=$HF_TOKEN --name tpu-test vllm-tpu /bin/bash -c "python3 -m pip install git+https://github.com/thuml/depyf.git && python3 -m pip install pytest && pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py && python3 /workspace/vllm/tests/tpu/test_compilation.py && python3 /workspace/vllm/examples/offline_inference_tpu.py"