A Gradio Web UI for running local LLM on Intel GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max) using IPEX-LLM.
GNU Affero General Public License v3.0
14
stars
8
forks
source link
Add model.half() when model load #25
Closed
hkvision closed 5 months ago
@sgwhat To save some memory?
Related issue may: https://github.com/intel-analytics/ipex-llm/issues/10575 If on Arc750