Commit History

v4.0: Production-grade optimizations - priority queue, prefix caching, TTL, metrics, TTFT tracking
c9737d6
Running

Matrix Agent commited on

v3.2: Speed optimizations - OpenBLAS, dual models (7B/1.5B), model selector, timing display
1b50d66

Matrix Agent commited on

Add frontend dashboard, comprehensive docs, and enhanced logging v3.1
8910367

Matrix Agent commited on

Fix asyncio event loop error in QueuedRequest dataclass
c5b1f8b

Matrix Agent commited on

Upload app.py with huggingface_hub
ab30b6f
verified

likhonsheikh commited on

Upload app.py with huggingface_hub
9436565
verified

likhonsheikh commited on

Upload folder using huggingface_hub
7ef800a
verified

likhonsheikh commited on

Upload folder using huggingface_hub
9b2c0ff
verified

likhonsheikh commited on

Upload app.py with huggingface_hub
2cd298a
verified

likhonsheikh commited on

Upload app.py with huggingface_hub
c880d13
verified

likhonsheikh commited on

Upload app.py with huggingface_hub
49560dc
verified

likhonsheikh commited on

Upload app.py with huggingface_hub
dffa5d7
verified

likhonsheikh commited on

Upload app.py with huggingface_hub
b1751bb
verified

likhonsheikh commited on