hf_text-generation-inference/Makefile

31 lines
751 B
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: install-server install-router install-launcher
server-dev:
cd server && make run-dev
router-dev:
cd router && cargo run
2022-10-18 07:19:03 -06:00
run-bloom-560m:
text-generation-launcher --model-name bigscience/bloom-560m --num-shard 2
2022-10-18 07:19:03 -06:00
2022-10-27 06:25:29 -06:00
run-bloom-560m-quantize:
text-generation-launcher --model-name bigscience/bloom-560m --num-shard 2 --quantize
download-bloom:
bloom-inference-server download-weights bigscience/bloom
2022-10-18 07:19:03 -06:00
run-bloom:
text-generation-launcher --model-name bigscience/bloom --num-shard 8
2022-10-27 06:25:29 -06:00
run-bloom-quantize:
text-generation-launcher --model-name bigscience/bloom --num-shard 8 --quantize