Commit History
30 days ago
-
Phase A serving speedup: zero-copy state-cache expand (no deepcopy per decision)
Verified signature5c02833 -
Serving-path speedup: state-KV LRU cache + suffix diet (see inference/bench_serve.py)
Verified signature5ca406a
-
Add inference/: minimal self-contained Typical inference package
Verified signature002c12c