AGILLM-3.5 / distributed /inference

Commit History

Stop distributed inference on EOS
a18d8d3
verified

OpenTransformer commited on

Add AGILLM3.5 round 299 inference-slim checkpoint
66ed57c
verified

OpenTransformer commited on

Reduce distributed inference checkpoint memory
2fc5118
verified

OpenTransformer commited on

Add KV-cache distributed inference
3c06653
verified

OpenTransformer commited on

Add distributed inference harness
bafb727
verified

OpenTransformer commited on