hf_text-generation-inference/Makefile

45 lines
1.1 KiB
Makefile

install-server:
cd server && make install
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
server-dev:
cd server && make run-dev
router-dev:
cd router && cargo run -- --port 8080
integration-tests: install-router install-launcher
cargo test
python-server-tests:
HF_HUB_ENABLE_HF_TRANSFER=1 pytest server/tests
python-client-tests:
pytest clients/python/tests
python-tests: python-server-tests python-client-tests
run-bloom-560m:
text-generation-launcher --model-id bigscience/bloom-560m --num-shard 2 --port 8080
run-bloom-560m-quantize:
text-generation-launcher --model-id bigscience/bloom-560m --num-shard 2 --quantize --port 8080
download-bloom:
HF_HUB_ENABLE_HF_TRANSFER=1 text-generation-server download-weights bigscience/bloom
run-bloom:
text-generation-launcher --model-id bigscience/bloom --num-shard 8 --port 8080
run-bloom-quantize:
text-generation-launcher --model-id bigscience/bloom --num-shard 8 --quantize --port 8080