ryugyosoft
/

onw

Mixture of Experts

inference-engine

Model card Files Files and versions

onw / trace_experts.py

Commit History

Sep 26 24 days ago

15:13
v0.6.0: stream MoE experts from the SSD (LRU cache, direct I/O) when the model does not fit; expert memory setting

ryugyosoft

Verified signature
3a7bf50