hf_text-generation-inference/Makefile

40 lines
1.0 KiB
Makefile
Raw Normal View History

2022-10-18 07:19:03 -06:00
install-server:
cd server && make install
2022-10-18 07:19:03 -06:00
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:
2023-03-07 10:52:22 -07:00
cd router && cargo run -- --port 8080
2022-10-18 07:19:03 -06:00
integration-tests: install-router install-launcher
cargo test
python-tests:
cd server && HF_HUB_ENABLE_HF_TRANSFER=1 pytest tests
2022-10-18 07:19:03 -06:00
run-bloom-560m:
2023-03-07 10:52:22 -07:00
text-generation-launcher --model-id bigscience/bloom-560m --num-shard 2 --port 8080
2022-10-18 07:19:03 -06:00
2022-10-27 06:25:29 -06:00
run-bloom-560m-quantize:
2023-03-07 10:52:22 -07:00
text-generation-launcher --model-id bigscience/bloom-560m --num-shard 2 --quantize --port 8080
2022-10-27 06:25:29 -06:00
download-bloom:
2023-03-03 10:42:20 -07:00
HF_HUB_ENABLE_HF_TRANSFER=1 text-generation-server download-weights bigscience/bloom
2022-10-27 06:25:29 -06:00
2022-10-18 07:19:03 -06:00
run-bloom:
2023-03-07 10:52:22 -07:00
text-generation-launcher --model-id bigscience/bloom --num-shard 8 --port 8080
2022-10-27 06:25:29 -06:00
run-bloom-quantize:
2023-03-07 10:52:22 -07:00
text-generation-launcher --model-id bigscience/bloom --num-shard 8 --quantize --port 8080