Update model lookup to use filename instead of ID in get_model function 9f9c6d5 alexfremont commited on 4 days ago
Improve model unloading with explicit GPU memory cleanup and CUDA cache clearing 8a8fe7c alexfremont commited on 5 days ago
Add timestamps to memory monitoring logs and display outputs 8580232 alexfremont commited on 5 days ago
Improve Docker container memory monitoring with cgroup v1/v2 support and better logging 80a3544 alexfremont commited on 5 days ago
Improve system memory info formatting by using newlines instead of pipes fa98542 alexfremont commited on 5 days ago
Remove periodic memory status updates and related helper function 1c12662 alexfremont commited on 5 days ago
Remove system status endpoint and monitoring functionality e241d94 alexfremont commited on 5 days ago
Add memory status display with auto-refresh every 10 seconds 078f3c3 alexfremont commited on 5 days ago
Add system monitoring features and memory usage tracking for loaded models 6ba6dc7 alexfremont commited on 5 days ago
Disable prepared statement cache for pgbouncer compatibility db280f4 alexfremont commited on 5 days ago
Remove DELETE endpoint for model unload, keep POST alternative only 28b854e alexfremont commited on 5 days ago
Add POST endpoint alternative for unloading models from memory ca20804 alexfremont commited on 5 days ago
Add API endpoint to unload models from memory without database deletion db789ea alexfremont commited on 5 days ago
Improve model info formatting for cleaner display in API responses 1445bc9 alexfremont commited on 5 days ago
Add enhanced Gradio UI with tabs, table view and model details formatting df3bf97 alexfremont commited on 5 days ago
Replace gradio import syntax and remove unnecessary whitespace 77f06e1 alexfremont commited on 5 days ago
Remove unused imports and simplify FastAPI/Gradio dependencies 68a1cf9 alexfremont commited on 5 days ago
Refactor model loading to store metadata alongside pipelines in model_pipelines dict dfb1c84 alexfremont commited on 5 days ago
Add force_download param to model pipeline loader for manual cache refresh 638ed9d alexfremont commited on 5 days ago
Fix model logging to use display_name instead of name field c2cd706 alexfremont commited on 5 days ago
Update model logging to use hf_filename instead of model_name 419e526 alexfremont commited on 5 days ago
Move API key middleware to main.py and add startup/shutdown lifecycle management 5df1f2d alexfremont commited on 7 days ago
Clean up imports and remove unused code across API modules 3635acb alexfremont commited on 7 days ago
Update type hint from Dict|None to Union[Dict, None] in fetch_model_by_id 48b9b47 alexfremont commited on 7 days ago
Refactor API auth and add management endpoints for model loading/updating bccef3b alexfremont commited on 7 days ago
Add model management endpoints and database fetch functionality 0053356 alexfremont commited on 7 days ago
Add theme.css and queue endpoints to static asset routing whitelist 2c455c2 alexfremont commited on 9 days ago
Add exception for Gradio static assets in API authentication middleware 97bf0f2 alexfremont commited on 9 days ago
Merge Gradio UI into FastAPI app and standardize port to 7860 b26a6dc alexfremont commited on 9 days ago
Add Gradio UI service and update Docker config for dual API/UI setup 5160659 alexfremont commited on 9 days ago
Skip auth middleware for debug mode and HF Space container logs ba5d6d2 alexfremont commited on 9 days ago
Refactor API architecture with modular design and database integration e109700 alexfremont commited on 9 days ago
