MertandGitHub 23f1f87dd0 feat(ml): optimized model inference (#31750) ...

* add immich_model

* graph per shape

* decouple ocr from ort

* prepared graphs

* use f16 for accelerators

* preload all shapes

* warm-up pass after preload

* keep precision for fp32 graphs

* ensure padding for text recognition

* optimize postprocessing for fp16 outputs

* handle raw ctc logits

* use f16 output for rknn

* mmap token embedding

* read device metadata

2026-09-25 14:56:44 -04:00

..

models

feat(ml): optimized model inference (#31750)

2026-09-25 14:56:44 -04:00

sessions

feat(ml): optimized model inference (#31750)

2026-09-25 14:56:44 -04:00

__init__.py

chore(ml): installable package (#17153)

2025-03-27 19:49:09 +00:00

__main__.py

feat(ml): improve model loading (#31742)

2026-09-25 14:56:43 -04:00

allocator.py

feat(ml): improve model loading (#31742)

2026-09-25 14:56:43 -04:00

config.py

feat(ml): optimized model inference (#31750)

2026-09-25 14:56:44 -04:00

gunicorn_conf.py

chore(ml): installable package (#17153)

2025-03-27 19:49:09 +00:00

log_conf.json

chore(ml): installable package (#17153)

2025-03-27 19:49:09 +00:00

main.py

feat(ml): optimized model inference (#31750)

2026-09-25 14:56:44 -04:00

schemas.py

feat(ml): optimized model inference (#31750)

2026-09-25 14:56:44 -04:00