ipex-llm/docker/llm/serving/xpu/docker/start-lightweight_serving-service.sh
Wang, Jian4 b119825152
Remove tgi parameter validation (#11688)
* remove validation

* add min warm up

* remove no need source
2024-07-30 16:37:44 +08:00

4 lines
No EOL
175 B
Bash

cd /llm/lightweight_serving
model_path="/llm/models/Llama-2-7b-chat-hf"
low_bit="sym_int4"
python lightweight_serving.py --repo-id-or-model-path $model_path --low-bit $low_bit