Hitonabi 35dcc69ba5 Implement prompt caching, speculative decoding config, parallel slots, and dynamic pricing metrics

2026-06-26 14:00:32 +02:00

..

routers

Implement prompt caching, speculative decoding config, parallel slots, and dynamic pricing metrics

2026-06-26 14:00:32 +02:00

services

Implement prompt caching, speculative decoding config, parallel slots, and dynamic pricing metrics

2026-06-26 14:00:32 +02:00

app.py

fix: serve manifest.webmanifest and other root files in SPA catch-all

2026-06-25 22:30:26 +02:00

config.py

Implement prompt caching, speculative decoding config, parallel slots, and dynamic pricing metrics

2026-06-26 14:00:32 +02:00

migrate_config.py

Implement prompt caching, speculative decoding config, parallel slots, and dynamic pricing metrics

2026-06-26 14:00:32 +02:00

requirements.txt

feat(2.0): implement cockpit improvements, dynamic mcp path, v2 venv, and ko-residency

2026-06-25 21:50:16 +02:00