Commit Graph
4 Commits
Author SHA1 Message Date
MertandGitHub ab159b8118 fix(ml): stricter typing and request validation (#31856) 2026-09-28 14:14:01 -04:00
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
MertandGitHub de13aab713 feat(ml): improve model loading (#31742)
* use recent mimalloc

* jit caching

* bump onnxruntime-gpu

* explicit memory release

* refactor in-memory cache

* configure hf org and revision

* refactor model load

* move orjson response

* disable direct submission for i915

* flush denormals

* update tests and lock

* disable suboptimal fusions

* respect resize_mode

* increase threads for clip text
2026-09-25 14:56:43 -04:00
MertandGitHub 84c35e35d6 chore(ml): installable package (#17153)
* app -> immich_ml

* fix test ci

* omit file name

* add new line

* add new line
2025-03-27 19:49:09 +00:00