Commit Graph

16 Commits

Author SHA1 Message Date
Mert
2b37caba03 feat(ml): rocm (#16613)
* feat(ml): introduce support of onnxruntime-rocm for AMD GPU

* try mutex for algo cache

use OrtMutex

* bump versions, run on mich

use 3.12

use 1.19.2

* acquire lock before any changes can be made

guard algo benchmark results

mark mutex as mutable

re-add /bin/sh (?)

use 3.10

use 6.1.2

* use composite cache key

1.19.2

fix variable name

fix variable reference

aaaaaaaaaaaaaaaaaaaa

* bump deps

* disable algo caching

* fix gha

* try ubuntu runner

* actually fix the gha

* update patch

* skip mimalloc preload for rocm

* increase build threads

* increase timeout for rocm

* Revert "increase timeout for rocm"

This reverts commit 2c4452f5d132198ed381a7b262b4a5cab5114b5f.

* attempt migraphx

* set migraphx_home

* Revert "set migraphx_home"

This reverts commit c121d3e48754b3bce100636f8d666deec58a44b7.

* Revert "attempt migraphx"

This reverts commit 521f9fb72dbe506dc6cb8faeb6494817d87265c6.

* migraphx, take two

* bump rocm

* allow cpu

* try only targeting migraphx

* skip tests

* migraph 

* known issues

* target gfx900 and gfx1102

* mention `HSA_USE_SVM`

* update lock

* set device id for rocm

---------

Co-authored-by: Mehdi GHESH <mehdi.ghesh@hotmail.fr>
2025-03-17 21:08:19 +00:00
Yoni Yang
14c3b99c0f feat(ml): ML on Rockchip NPUs (#15241) 2025-03-17 12:04:08 -04:00
Mert
2e5007adef docs: soften wording for openvino igpu (#15941) 2025-02-07 06:44:22 -05:00
Alex
6239365f68 chore(docs): clean up and add new content (#15003)
* wip: Install

* wip: sharing

* wip: features

* wip: features

* wip: tags and folder view

* update links

* fix: broken reference to page sections

* pr feedback

* Update docs/docs/overview/comparison.md

Co-authored-by: Daniel Dietzler <36593685+danieldietzler@users.noreply.github.com>

* webp

* webp is glory

* webp is glory

---------

Co-authored-by: Daniel Dietzler <36593685+danieldietzler@users.noreply.github.com>
2025-01-02 10:04:14 -06:00
Mert
bd826b0b9b feat(ml): round-robin device assignment (#13237)
* round-robin device assignment

* docs and tests

clarify doc
2024-10-07 17:37:45 -04:00
Mert
ad58d7e23e chore(ml): downgrade to cuda 12.2 (#12587)
* downgrade to cuda 12.2

* update docs
2024-09-12 00:25:57 +00:00
renovate[bot]
b53bd8c525 fix(deps): update machine-learning (#10740)
* fix(deps): update machine-learning

* update openvino options, cuda

* update openvino build

* fix indentation

* update minimum nvidia driver

---------

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2024-07-21 19:30:24 -04:00
Fynn Petersen-Frey
54488b1016 feat(ml): improved ARM-NN support (#11233) 2024-07-20 15:59:27 -04:00
Jason Rasmussen
4807fc40a6 refactor!: LOG_LEVEL => IMMICH_LOG_LEVEL (#9557)
refactor: LOG_LEVEL => IMMICH_LOG_LEVEL
2024-05-17 11:44:22 -04:00
Mert
ad915ccd64 docs(ml): update link (#9477)
update link
2024-05-14 15:34:36 +01:00
Mert
a90138e42e docs(ml): clarify cuda and openvino requirements (#9072)
update docs
2024-04-24 23:15:26 -05:00
aviv926
58e516c766 Docs: minor changes (#8814)
* minor

* add image

* PR feedback

* npm run format:fix of course 4_4

* Remove what is not relevant

* pr feedback

* PR feedback

* revert npm run format

* Update docs/docs/FAQ.mdx

Co-authored-by: Ben McCann <322311+benmccann@users.noreply.github.com>

* Update FAQ.mdx

---------

Co-authored-by: Alex <alex.tran1502@gmail.com>
Co-authored-by: Ben McCann <322311+benmccann@users.noreply.github.com>
2024-04-16 07:26:12 +02:00
Mert
8c9a092561 docs(ml): update hardware acceleration doc (#8700)
* update docs

* formatting
2024-04-11 09:39:18 +02:00
Mert
b74c84e771 fix(docs): add cuda tag to ml hwaccel example (#6972)
add `-cuda`
2024-02-07 20:58:39 -06:00
Mert
329659b2fb docs(ml,server): updated hwaccel docs (#6878) 2024-02-03 09:11:53 -05:00
Mert
efdbe790ee docs(ml): hardware acceleration (#6821) 2024-01-31 19:12:57 -06:00