Files
oh-my-pi/docs
can1357 5d3adfab7f feat(tiny): added GPU-first device selection with CPU fallback for local models
- Added `PI_TINY_DEVICE` env var to control ONNX execution provider (`gpu` default, `cpu`, `metal`, `cuda`, `dml`, `coreml`).
- Local tiny-model inference now tries accelerated GPU provider first and retries on CPU if initialization fails.
- Added `device.ts` module with normalization, preference resolution, and load-order helpers.
- Updated docs and model descriptions to drop CPU-specific language.
2026-05-31 01:57:59 +02:00
..
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-05-14 21:32:31 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00
2026-04-30 06:47:01 +02:00