Spaces:
Running on Zero
Running on Zero
Commit History
-
fix: bind dummy worker to hidden Gradio button for HF ZeroGPU check and add class 38 to LabelRegistry
f56867f
-
fix(security): handle query parameters in HMAC signature and default API key fallback
790c991 -
feat: pre-download all 8 AI models on boot via huggingface_hub SDK
5fc4228 -
fix: use hf_hub_download SDK and validate >1MB binary size to prevent text-pointer segfaults
04d56e6 -
fix: mount Gradio at root / and restore background model download & warmup task
bdc8261 -
fix: report status healthy when models_ready is True for Hugging Face health check probe
38d3256 -
fix: pre-warm models synchronously during lifespan startup to guarantee zero-downtime container readiness
d055536 -
fix: harden health check exception handling and fix cnn_loaded state calculation
69af453 -
fix: use streamed chunk download with User-Agent header for HF Hub model binaries
3982649 -
fix: add safe fallback to yolo_service for missing ONNX models during warmup
d2d1629 -
perf: prioritize fast and limited model download and warmup on boot
bc9c615 -
fix: use direct HF resolve download to guarantee binary model files without pointer file corruption
29ea819 -
perf: optimize model_loader manifest to download essential ONNX models for rapid boot
34ce6c6 -
perf: refine warmup to pre-warm primary production models within RAM budget
9f53731 -
fix: export environment variables in app/__init__.py for module resolution
66c5614 -
perf: reuse existing ONNX sessions across modes pointing to identical model paths
ad22f50 -
fix: enforce explicit CPUExecutionProvider to prevent CUDA device discovery segfaults on HF CPU space
0c272c4 -
fix: add 1.0s timeout to DB and Redis checks in health endpoint to prevent proxy 503 timeouts
cd69f93 -
fix: set relative data/ model default paths in config.py for portable environment execution
379216b -
fix: remove non-ASCII unicode characters from print calls in model_loader.py
22edca0 -
perf: non-blocking async model warmup for instant boot and 200 OK health check
8563384 -
fix: add root GET / health response route for HF ingress proxy
b8299ee -
fix: safe redis connection check and graceful fallback
586a69a -
fix: default rate_limiter to memory:// when local redis is used
c229cda -
feat: launch uvicorn with full mounted app and add /api/v1/health route
5b75e17 -
fix: in-memory fallback for rate limiter when redis is unreachable
827e99a -
feat: migrate full production detection service architecture with 8-model hub sync
119c847