14 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
bo0tzz
882163f545
chore: build metadata for ML container (#15831)
* chore: build metadata for ML container

* fix: build_image_url
2025-02-02 23:45:58 +01:00
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
Richard Kojedzinszky
f3e176e192
feat(ml): support dynamic scaling (#12065)
feat(ml): make http keep-alive configurable

Closes #12064
2024-08-29 15:11:49 +00:00
Mert
173c9070c8
fix(ml): re-add worker env (#11192)
re-add worker env
2024-07-18 17:50:52 +00:00
Mert
88f62087fd
chore(ml): set higher worker timeout for openvino (#11174) 2024-07-18 10:50:57 -04:00
Jason Rasmussen
d61418886f
refactor!: port env (#9559)
refactor: port env
2024-05-17 12:59:05 -04:00
Mert
3a045b33ca
chore(deps): update onnxruntime-openvino (#7854) 2024-03-16 00:04:45 -04:00
Andrew Rowson
37e5b91dc2
fix(server): ml gunicorn listen on ipv4 and ipv6 by default (#7930) 2024-03-13 12:13:56 -05:00
martin
ddae707ea9
fix: shell scripts (#7186)
* fix: bash scripts

* pr feedback

* wrong variable

* ci: add shellcheck workflow

* fix: missing scripts
2024-02-18 17:03:01 -06:00
Mert
d729c863c8
chore(ml): improve shutdown (#5689) 2023-12-14 13:51:24 -06:00
Mert
0a24ff90bb
fix(ml): set higher default worker timeout (#4007) 2023-09-07 08:27:29 +07:00
Mert
b7fd5dcb4a
dev(ml): fixed docker-compose.dev.yml, updated locust (#3951)
* fixed dev docker compose

* updated locustfile

* deleted old script, moved comments to locustfile
2023-09-01 21:59:17 -04:00
Mert
41461e0d5d
chore(ml): memory optimisations (#3934) 2023-08-31 18:30:53 -05:00