text-generation-inference/Makefile
Mohit Sharma 557e18e08c fix style
2024-06-24 14:30:26 +00:00

59 lines
1.5 KiB
Makefile

install-server:
cd server && make install
install-server-cpu:
cd server && make install-server
install-router:
cd router && cargo install --path .
install-launcher:
cd launcher && cargo install --path .
install-benchmark:
cd benchmark && cargo install --path .
install: install-server install-router install-launcher
install-cpu: install-server-cpu install-router install-launcher
server-dev:
cd server && make run-dev
router-dev:
cd router && cargo run -- --port 8080
rust-tests: install-router install-launcher
cargo test
install-integration-tests:
cd integration-tests && pip install -r requirements.txt
cd clients/python && pip install .
integration-tests: install-integration-tests
pytest -s -vv -m "not private" integration-tests
update-integration-tests: install-integration-tests
pytest -s -vv --snapshot-update integration-tests
python-server-tests:
HF_HUB_ENABLE_HF_TRANSFER=1 pytest -s -vv -m "not private" server/tests
python-client-tests:
pytest clients/python/tests
python-tests: python-server-tests python-client-tests
run-falcon-7b-instruct:
text-generation-launcher --model-id tiiuae/falcon-7b-instruct --port 8080
run-falcon-7b-instruct-quantize:
text-generation-launcher --model-id tiiuae/falcon-7b-instruct --quantize bitsandbytes --port 8080
clean:
rm -rf target aml
interact:
docker run --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 64g --net host -v /home/mohit/.cache/huggingface/hub/:/data -v $(PWD):/tgi tgi-mht