search

flexflow / FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving
https://flexflow.readthedocs.io
Apache License 2.0
1.6k stars 219 forks source link

Modify model cache path #1320

Open lockshaw opened 4 months ago

lockshaw commented 4 months ago 
          > @1193749292 We'll add a non-verbose inference mode soon. In the meantime, feel free to comment out the print statements that you don't need

hi, I wonder how to modify the cache path, I don't want cache model's weights in ~/.cache/flexflow, thanks!

Originally posted by @xinlong-yang in https://github.com/flexflow/FlexFlow/issues/1236#issuecomment-1916484066

lockshaw commented 4 months ago

@goliaro Does inference support XDG_CACHE_HOME?