mirror of
https://github.com/mudler/LocalAI.git
synced 2026-04-27 22:02:14 -05:00
c9451cb604
* Bump oneapi-basekit, optimum and openvino * Changed PERFORMANCE HINT to CUMULATIVE_THROUGHPUT Minor latency change for first token but about 10-15% speedup on token generation.
Creating a separate environment for the transformers project
make transformers