⚡ Bolt: [performance improvement] Optimize math normalization in ONNX inference output

⚡ Bolt: Parallelize payload encoding in /predict

perf: optimize colormap matrix mult

Optimized inference memory conversions and API bytes manipulation.

⚡ Bolt: [performance improvement] parallelize colormap lut initialization

⚡ Bolt: [performance improvement] optimize LUT init and prevent async loop blocking

⚡ Bolt: [performance improvement] In-place ONNX array mutation

⚡ Bolt: Optimize API windspeed lookup and inference operations

Optimize inference: ONNX session opts + pre-computed colormap LUT

perf: Avoid unnecessary float32 array allocation during inference

Optimize gzip and PNG compression levels for API latency

perf: Avoid NumPy to Python list conversion overhead in inference output processing

⚡ Bolt: [performance improvement] Optimize _color_to_windspeed array reshaping and distance calculation

Optimize `_color_to_windspeed` pairwise distance calculation

Fixes

Update api.py

Overhaul

Initial commit