Merge pull request #21 from Eddy3D-Dev/dependabot/uv/requests-2.33.0

Merge pull request #22 from Eddy3D-Dev/dependabot/uv/pygments-2.20.0

chore(deps): bump pygments from 2.19.2 to 2.20.0

chore(deps): bump requests from 2.32.5 to 2.33.0

Merge pull request #16 from Eddy3D-Dev/bolt-performance-improvement-fma-numpy-7921326008298019622

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

Merge pull request #15 from Eddy3D-Dev/bolt-parallel-payload-encoding-17637346567941703638

⚡ Bolt: Parallelize payload encoding in /predict

Merge pull request #14 from Eddy3D-Dev/bolt-colormap-matrix-opt-17229212821387937058

perf: optimize colormap matrix mult

Merge pull request #13 from Eddy3D-Dev/bolt-optimize-inference-memory-8246253676241586361

Optimized inference memory conversions and API bytes manipulation.

Merge pull request #12 from Eddy3D-Dev/perf-colormap-lut-startup-13694817526022920845

⚡ Bolt: [performance improvement] parallelize colormap lut initialization

Merge pull request #11 from Eddy3D-Dev/bolt-perf-async-def-and-lut-init-7321735563256430450

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

Merge pull request #10 from Eddy3D-Dev/bolt-in-place-onnx-output-4891877662814159698

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

Merge pull request #9 from Eddy3D-Dev/bolt-performance-improvement-1-1556830431954544929

⚡ Bolt: Optimize API windspeed lookup and inference operations

Merge pull request #8 from Eddy3D-Dev/claude/optimize-inference-performance-09SbO

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

Merge pull request #7 from Eddy3D-Dev/bolt-optimize-astype-11350113284348635439

perf: Avoid unnecessary float32 array allocation during inference

Merge pull request #6 from Eddy3D-Dev/bolt-performance-gzip-7233662022417404229

Optimize gzip and PNG compression levels for API latency

Merge pull request #5 from Eddy3D-Dev/bolt-numpy-list-overhead-231724176492942719

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

Merge pull request #4 from Eddy3D-Dev/bolt-perf-color-to-windspeed-4165902933064401210

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

Remove Render deployment section from README

Merge pull request #3 from Eddy3D-Dev/bolt-optimize-color-to-windspeed-5497494537476708673

Optimize `_color_to_windspeed` pairwise distance calculation

Add API import test to deployment workflow

Update huggingface.yml

Fixes

Add syntax check to huggingface deployment workflow

Update api.py

docs: fix api status badge to use json endpoint

docs: add hugging face space and api health badges

docs: add hugging face space endpoint to readme

Update .gitattributes

ci: force push to Hugging Face Space

ci: add action to sync with Hugging Face Space

chore: add Hugging Face Space configuration

Bump pillow and python-multipart

Overhaul

Initial commit