Commit Graph

22 Commits

Author SHA1 Message Date
dependabot[bot]
62e6528a86
Update onnxruntime-gpu requirement in /docker/tensorrt
Updates the requirements on [onnxruntime-gpu](https://github.com/microsoft/onnxruntime) to permit the latest version.
- [Release notes](https://github.com/microsoft/onnxruntime/releases)
- [Changelog](https://github.com/microsoft/onnxruntime/blob/main/docs/ReleaseManagement.md)
- [Commits](https://github.com/microsoft/onnxruntime/commits)

---
updated-dependencies:
- dependency-name: onnxruntime-gpu
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-11-21 11:45:43 +00:00
Austin Kirsch
c1bfc1df67
fix tensorrt model generation variable (#14902) 2024-11-10 16:23:32 -06:00
Nicolas Mowen
46ed520886
Don't generate tensorrt models by default (#14865) 2024-11-08 07:37:18 -06:00
Nicolas Mowen
bb4e863e87
Fix jetson onnxruntime (#14698)
* Fix jetson onnxruntime

* Remove comment
2024-10-30 19:16:28 -05:00
Nicolas Mowen
c7a4220d65
Jetson onnxruntime (#14688)
* Add support for using onnx runtime with jetson

* Update docs

* Clarify
2024-10-30 08:22:28 -06:00
Nicolas Mowen
f9fba94863
Slightly downgrade onnxruntime-gpu (#14558) 2024-10-24 13:17:11 -05:00
Nicolas Mowen
f9b246dbd0
Deps updates (#14556)
* Update nvidia deps

* Update python deps

* Update web deps
2024-10-24 08:48:14 -05:00
Nicolas Mowen
1a51ce712c
Simplify tensorrt building (#13851)
* Simplify tensorrt building

* Use engine context cache
2024-09-20 10:49:44 -05:00
gtsiam
8573016bef
Formatting improvements (#13765)
* Format makefiles

* Handle all errors in rocm makefile

* Remove CURRENT_UID and GID from makefile as they are unused

* Removed unused vite.svg asset

* Sort frigate-dictionary
2024-09-17 07:39:44 -05:00
Nicolas Mowen
36d7eb7caa
Support ONNX model caching (#13780)
* Support model caching

* Cleanup
2024-09-16 18:18:11 -06:00
Nicolas Mowen
2f69f5afe6
Add support for yolonas via ONNX and allow TensorRT execution provider to work correctly (#13776)
* Add support for yolonas in onnx

* Add correct deps

* Set ld library path

* Refactor cudnn to only be used in amd64

* Add onnx to docs and add explainer at the top

* Undo change

* Update comment

* Remove uneccesary

* Remove line change
2024-09-16 16:17:31 -05:00
Nicolas Mowen
e4ea35e626
Add onnxruntime nvidia providers (#13756) 2024-09-15 20:30:30 -05:00
Nate Meyer
390403d957
Pass computes value to libyolo_layer build (#10210) 2024-03-05 06:04:13 -06:00
Nicholas Page
49814b34d3
Update Jetson ffmpeg patch for Jetpack 5.1.2 compatibility (#8914) 2023-12-31 07:38:29 -06:00
Nicolas Mowen
e1a6398219
Fix trt build (#8091) 2023-10-07 09:51:02 -05:00
Felipe Santos
3a460133d4
Add docker healthcheck (#8006)
* Add docker healthcheck

* Fix unknown start-interval

* Add HEALTHCHECK for tensorrt and bump default start-period

* Move healthcheck to deps stage
2023-10-07 09:21:03 -05:00
Nate Meyer
0d6bb6714a
Add support for selecting a specific GPU to use when converting TRT models (#7857) 2023-09-21 05:23:51 -05:00
Andrew Reiter
318ae28004
Revert numpy upgrade in -tensorrt image (#7348) 2023-08-05 05:49:06 -05:00
Andrew Reiter
7d3e5c9c4c
Revert numpy upgrade (#7341)
* Revert numpy upgrade

* Upgrade arm64 onnx version to match amd64

* Increase CODEOWNERS granularity

Not sure if it has an effect since I don't have repository write access
2023-07-31 21:45:50 -05:00
Nate Meyer
b42e995f0f
Update OpenVINO 2022.3.1 (#7319)
* Use build platform for running OpenVino model conversion

* Update OpenVINO to 2022.3.1 and upgrade numpy
2023-07-28 19:27:53 -05:00
Andrew Reiter
a96a951e23
Nvidia Jetson ffmpeg + TensorRT support (#6458)
* Non-Jetson changes

Required for later commits:
- Allow base image to be overridden (and don't assume its WORKDIR)
- Ensure python3.9
- Map hwaccel decode presets as strings instead of lists
Not required:
- Fix existing documentation
- Simplify hwaccel scale logic

* Prepare for multi-arch tensorrt build

* Add tensorrt images for Jetson boards

* Add Jetson ffmpeg hwaccel

* Update docs

* Add CODEOWNERS

* CI

* Change default model from yolov7-tiny-416 to yolov7-320

In my experience the tiny models perform markedly worse without being
much faster

* fixup! Update docs
2023-07-26 05:50:41 -05:00
Nicolas Mowen
dc44a6c3b4
Community Supported Boards Framework (#7114)
* Make main frigate build non rpi specific and build rpi using base image

* Add boards to sidebar

* Fix docker build

* Fix docs build

* Update pr branch for testing

* remove target from rpi build

* Remove manual build

* Add push build for rpi

* fix typos, improve wording

* Add arm build for rpi

* Cleanup and add default github ref name

* Cleanup docker build file system

* Setup to use docker bake

* Add ci/cd for bake

* Fix path

* Fix devcontainer

* Set targets

* Fix build

* Fix syntax

* Add wheels target

* Move dev container to trt

* Update key and fix rpi local

* Move requirements files and set intermediate targets

* Add back --load

* Update docs for community board development

* Update installation docs to reflect different builds available

* Update docs with official and community supported headers

* Update codeowners docs

* Update docs

* Assemble main and standard builds

* Change order of pushes

* Remove community board after successful build

* Fix rpi bake file names
2023-07-23 16:45:29 -05:00