[AI] GPU acceleration install: manifest-driven scripts by andriiryzhkov · Pull Request #20676 · darktable-org/darktable

andriiryzhkov · 2026-03-26T13:03:31Z

Follow-up to #20647 (ORT library path preference and custom loading). Addresses #20532.

Summary

Manifest-driven system for installing GPU-accelerated ONNX Runtime directly from darktable or via scripts.

Package manifest (`data/ort_gpu.json`)

All download URLs, SHA-256 checksums, archive formats, and ROCm version mappings in a single JSON file – update it to change URLs/versions without rebuilding darktable. Supports NVIDIA (CUDA), AMD (MIGraphX), and Intel (OpenVINO) on Linux and Windows.

Unified install scripts

Script	Platform	Requires
`install-ort-gpu.sh`	Linux	jq
`install-ort-gpu.ps1`	Windows	PowerShell
`install-ort-amd-build.sh`	Linux	cmake, gcc, python3

Scripts read the same ort_gpu.json manifest, detect GPU, download and verify the matching package. Support --vendor, --force, --manifest flags.

Documentation

tools/ai/README.md – install methods, EP table, manifest format, manual install, verification.

andriiryzhkov · 2026-04-02T09:51:44Z

@TurboGit : I need help testing this scripts and UI installer. Can you test it with NVIDIA card on Linux?

And maybe you can advise who can help with other tests?

TurboGit · 2026-04-02T16:46:57Z

@andriiryzhkov : Just to be sure, you mean install-ort-gpu.sh, right?

I'll try to do that tomorrow.

andriiryzhkov · 2026-04-02T18:08:33Z

@TurboGit :

install-ort-gpu.sh is a first part.
The second part (basically the same result) is "install" button added in AI preferences tab.

TurboGit · 2026-04-03T15:17:48Z

@andriiryzhkov : Using the script was ok. I was also able to install with the in UI [install] button. I saw a difference, when using the script I had not softlink created whereas with the in UI installation I got:

libonnxruntime.so -> libonnxruntime.so.1
libonnxruntime.so.1 -> libonnxruntime.so.1.24.4

andriiryzhkov · 2026-04-03T17:12:04Z

@TurboGit : Thank you for testing.

The symlinks are created by the UI install for extra safety, but not strictly required — darktable loads the library by full path from the preferences config, not via LD_LIBRARY_PATH or soname resolution. The script works fine without them since it provides the full path directly. I can add symlink creation to the script too for consistency if you prefer.

Looks like NVIDIA and AMD are tested.

TurboGit · 2026-04-03T17:24:08Z

I can add symlink creation to the script too for consistency if you prefer.

No not needed, just wanted to be sure this was expected and not the a cause of another issue.

andriiryzhkov · 2026-04-08T11:48:17Z

Fixed cuDNN detection in UI installation on Ubuntu and Debian

da-phil · 2026-04-14T11:02:34Z

Some feedback after I tried to install the ONNX runtime for ROCm 7.2, / MIGraphX:

❯ ./install-ort-gpu.sh --vendor amd --manifest ort_gpu.jsononnx
Vendor override: amd (skipping GPU detection)

ONNX Runtime 1.23.2 - GPU acceleration installer
============================================================

GPU: AMD GPU
ORT version: 1.23.2
Download size: ~300 MB
Install to: /home/phil/.local/lib/onnxruntime-migraphx
Requirements: ROCm 7.2, MIGraphX

Continue? [y/N] y

Downloading...
/tmp/tmp.V9P1P4uMDj/ort-package              100%[===========================================================================================>]  19,55M  10,7MB/s    in 1,8s    
Verifying checksum...
Checksum OK.
Extracting...

Done. Installed to: /home/phil/.local/lib/onnxruntime-migraphx
-rwxr-xr-x 1 phil phil 560K Apr 14 12:35 /home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime_providers_migraphx.so
-rwxr-xr-x 1 phil phil  16K Apr 14 12:35 /home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime_providers_shared.so
-rwxr-xr-x 1 phil phil  27M Apr 14 12:35 /home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2

To enable in darktable:

  1. Open darktable preferences (Ctrl+,)
  2. Go to the AI tab
  3. Click 'detect' to find the installed library automatically,
     or set 'ONNX Runtime library' to:
     /home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2
  4. Restart darktable

Or via command line:

  DT_ORT_LIBRARY=/home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2 darktable

Now this is what I get when I start darktable with ai debug msgs enabled and click on the restore module:

❯ DT_ORT_LIBRARY=/home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2 darktable -d ai
darktable 5.5.0+965~g44a4e93598-dirty
Copyright (C) 2012-2026 Johannes Hanika and other contributors.

Compile options:
  Bit depth              -> 64 bit
  Exiv2                  -> 0.27.6
  Lensfun                -> 0.3.4
  Debug                  -> DISABLED
  SSE2 optimizations     -> ENABLED
  OpenMP                 -> ENABLED
  OpenCL                 -> ENABLED
  Lua                    -> ENABLED  - API version 9.6.0
  Colord                 -> DISABLED
  gPhoto2                -> ENABLED  - Camera tethering is available
  OSMGpsMap              -> DISABLED - Map view is NOT available
  GMIC                   -> ENABLED  - Compressed LUTs are supported
  GraphicsMagick         -> ENABLED
  ImageMagick            -> DISABLED
  libavif                -> ENABLED
  libheif                -> ENABLED
  libjxl                 -> ENABLED
  LibRaw                 -> ENABLED  - Version 0.22.0-Release
  OpenJPEG               -> ENABLED
  OpenEXR                -> ENABLED
  WebP                   -> ENABLED
  AI                     -> ENABLED

See https://www.darktable.org/resources/ for detailed documentation.
See https://github.com/darktable-org/darktable/issues/new/choose to report bugs.

[dt starting] as : darktable -d ai
     0,3188 [ai_models] initialized: models_dir=/home/phil/.local/share/darktable/models, cache_dir=/home/phil/.cache/darktable/ai_downloads
     0,3191 [ai_models] using repository: darktable-org/darktable-ai
     0,3191 [ai_models] registered model: mask sam2.1 hiera small (mask-object-sam21-small)
     0,3191 [ai_models] registered model: mask segnext vitb-sax2 hq (mask-object-segnext-b2hq)
     0,3191 [ai_models] registered model: denoise nind (denoise-nind)
     0,3191 [ai_models] registered model: upscale bsrgan (upscale-bsrgan)
     0,3191 [ai_models] registry loaded: 4 models from /opt/darktable/share/darktable/ai_models.json
     2.8004 [darktable_ai] dt_ai_env_init start.
     2.8005 [darktable_ai] discovered: upscale bsrgan (upscale-bsrgan, backend=onnx)
     2.8005 [darktable_ai] discovered: mask sam2.1 hiera small (mask-object-sam21-small, backend=onnx)
     2.8005 [darktable_ai] discovered: denoise nind (denoise-nind, backend=onnx)
     2.8006 [darktable_ai] discovered: mask segnext vitb-sax2 hq (mask-object-segnext-b2hq, backend=onnx)
    20.7755 [neural_restore] preview: exported 9568x6376, scale=1, export_size=0
    20.7986 [darktable_ai] loaded ORT 1.23.2 from '/home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2'
The requested API version [24] is not available, only API versions [1, 23] are supported in this build. Current ORT Version is: 1.23.2
    20.7987 [darktable_ai] ORT 1.23.2: using API version 23 (compiled for 24)
    20.7987 [darktable_ai] execution provider: MIGraphX
    20.7993 [darktable_ai] MIOpen cache: /home/phil/.cache/darktable/ai/amd/miopen
    20.7993 [darktable_ai] MIGraphX cache: /home/phil/.cache/darktable/ai/amd/migraphx
    20.8158 [darktable_ai] loading: /home/phil/.local/share/darktable/models/denoise-nind/model.onnx
    20.8160 [darktable_ai] attempting to enable AMD MIGraphX...
    20.9144 [darktable_ai] AMD MIGraphX enabled successfully.
2026-04-14 12:50:36.136523057 [W:onnxruntime:DarktableAI, migraphx_execution_provider.cc:167 MIGraphXExecutionProvider] [MIGraphX EP] MIGraphX ENV Override Variables Set:
2026-04-14 12:50:36.431876117 [W:onnxruntime:DarktableAI, migraphx_execution_provider.cc:1309 compile_program] Model Compile: Begin

It just gets stuck with Model Compile: Begin, while my GPU gets very busy and hot.

I also attached the output of rocminfo: rocminfo.txt.
And here are all installed rocm/migraph pkgs: rocm_migraph_pkgs.txt

I assigned 10 GB of pageable RAM to the iGPU, which should be sufficient, shouldn't it?

❯ amd-ttm
💻 Current TTM pages limit: 2621440 pages (10.00 GB)
💻 Total system memory: 30.64 GB

It is certainly not hitting any memory bottleneck as per the amd-smi overview:

❯ amd-smi
+------------------------------------------------------------------------------+
| AMD-SMI          26.4.0+478a7a43c6                                           |
| OS kernel Version:  6.18.20-061820-generic                                      |
| ROCm Version:    7.13.0                                                      |
| VBIOS Version:   00077464                                                    |
| Platform:        Linux Baremetal                                             |
|-------------------------------------+----------------------------------------|
| BDF                        GPU-Name | Mem-Uti   Temp   UEC       Power-Usage |
| GPU  HIP-ID  OAM-ID  Partition-Mode | GFX-Uti    Fan               Mem-Usage |
|=====================================+========================================|
| 0000:65:00.0 ...adeon 780M Graphics | N/A        N/A   0                 N/A |
|   0       0     N/A             N/A | N/A        N/A           3128/10240 MB |
+-------------------------------------+----------------------------------------+
+------------------------------------------------------------------------------+
| Processes:                                                                   |
|  GPU      PID  Process Name       GTT_MEM  VRAM_MEM  MEM_USAGE  CU %  SDMA   |
|==============================================================================|
|    0   646843  darktable           1.3 GB    5.5 MB     1.3 GB    N/A   0 us |
+------------------------------------------------------------------------------+

Maybe this is just a very specific AMD / iGPU issue, as my laptop is running on a AMD Ryzen 7 8845HS with an Radeon 780M iGPU.

andriiryzhkov · 2026-04-14T11:27:26Z

@da-phil :

It just gets stuck with Model Compile: Begin, while my GPU gets very busy and hot.

You are not stuck, let it finish compilation. It may take long, veeerrrryyyyy long. But it's only one time per model and per tile size. I tested on my Radeon 780M iGPU and it took 30 minutes. The compilation is cached on disk. The following runs with the same tile size where very fast - just like 10 seconds or so. Much faster than CPU.

iGPUs generally are not supported by ROCm and they don't have pre-build kernels. That's why I think it takes so long. But compilation is a thing even for proper supported GPUs.

da-phil · 2026-04-14T12:51:19Z

@da-phil :

It just gets stuck with Model Compile: Begin, while my GPU gets very busy and hot.

You are not stuck, let it finish compilation. It may take long, veeerrrryyyyy long. But it's only one time per model and per tile size. I tested on my Radeon 780M iGPU and it took 30 minutes. The compilation is cached on disk. The following runs with the same tile size where very fast - just like 10 seconds or so. Much faster than CPU.

iGPUs generally are not supported by ROCm and they don't have pre-build kernels. That's why I think it takes so long. But compilation is a thing even for proper supported GPUs.

Okay, this time I was patient enough and voila, it worked!
Processing a 9568x6376 image on the iGPU was significantly faster than on the CPU, by a factor of 3.2x (55.29s VS 178.33s)!

On CPU:

   224.1143 [neural_restore] job started: task=denoise, scale=1, images=1
   224.1163 [neural_restore] processing imgid 63525 -> /home/phil/Pictures/some_image.tif
   229.3276 [neural_restore] processing 9568x6376 -> 9568x6376 (scale=1)
   229.3280 [restore] tiling 9568x6376 (scale=1) -> 9568x6376, 7x5 grid (35 tiles, T=1536)
   402.4445 [neural_restore] imported imgid=63529: /home/phil/Pictures/some_image.tif

On GPU:

  1980.9891 [neural_restore] job started: task=denoise, scale=1, images=1
  1980.9913 [neural_restore] processing imgid 63525 -> /home/phil/Pictures/some_image.tif
  1984.5201 [neural_restore] processing 9568x6376 -> 9568x6376 (scale=1)
  1984.5211 [restore] tiling 9568x6376 (scale=1) -> 9568x6376, 7x5 grid (35 tiles, T=1536)
  2036.2812 [neural_restore] imported imgid=63530: /home/phil/Pictures/some_image.tif

But now the problem: the GPU path leads to significant vertical stripe artifacts:

Is this a known issue or is there anything I can do to debug it? The CPU path leads to artifact-free denoised images.

andriiryzhkov · 2026-04-14T12:54:37Z

But now the problem: the GPU path leads to significant vertical stripe artifacts

That is interesting. I will check, but assume it would be hard to trace

da-phil · 2026-04-14T18:24:01Z

When testing your changes from PR #20813, I stopped seeing those vertical stripes and the export speed increased to a solid average of 46s for the same 9568x6376 image. Will get back to you once I know more or if I can reproduce the issue.

andriiryzhkov · 2026-04-16T17:43:49Z

@TurboGit : This PR is ready for review. I personally tested on all three platforms and major GPU vendors. The only combination that I don't have opportunity to test is OpenVINO on Linux. That is for Intel iGPU or GPU. It could be just iGPU with Intel processor. I don't expect any problems with it, but just transparent about this small gap.

PR is general provides easy way to deal with different AI acceleration options from within darktable itself.

andriiryzhkov · 2026-04-28T08:51:20Z

@TurboGit : Can you have a look on this PR too?

da-phil · 2026-04-28T21:03:32Z

Sorry for providing feedback so late, but I gave the install script another spin with this outcome:

ONNX Runtime 1.23.2 - GPU acceleration installer
============================================================

GPU:          AMD Ryzen 7 5700X 8-Core Processor 
AMD GPU
Driver: ROCm 7.2.1
ORT version: 1.23.2
Download size: ~300 MB
Install to: /home/phil/.local/lib/onnxruntime-migraphx
Requirements: ROCm 7.2, MIGraphX

Continue? [y/N] y

Downloading...
/tmp/tmp.75ripQGP6m/ort-package                        100%[==========================================================================================================================>]  19,55M  10,1MB/s    in 1,9s    
Verifying checksum...
Checksum OK.
Extracting...

Done. Installed to: /home/phil/.local/lib/onnxruntime-migraphx
-rwxr-xr-x 1 phil phil 560K Apr 28 22:57 /home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime_providers_migraphx.so
-rwxr-xr-x 1 phil phil  16K Apr 28 22:57 /home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime_providers_shared.so
-rwxr-xr-x 1 phil phil  27M Apr 28 22:57 /home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2

To enable in darktable:

  1. Open darktable preferences (Ctrl+,)
  2. Go to the AI tab
  3. Click 'detect' to find the installed library automatically,
     or set 'ONNX Runtime library' to:
     /home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2
  4. Restart darktable

Or via command line:

  DT_ORT_LIBRARY=/home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2 darktable

It's a little bit misleading to see my CPU in this line:
"GPU: AMD Ryzen 7 5700X 8-Core Processor
AMD GPU"

Also, I'm a little bit confused why it chooses libonnxruntime.so.1.23.2, I thought DT is build with libonnxruntime.so.1.24?
Because I keep getting those messages when running model:

   568.5713 [darktable_ai] loaded ORT 1.23.2 from '/home/phil/.local/lib/onnxruntime-migraphx/libonnxruntime.so.1.23.2'
The requested API version [24] is not available, only API versions [1, 23] are supported in this build. Current ORT Version is: 1.23.2
   568.5713 [darktable_ai] ORT 1.23.2: using API version 23 (compiled for 24)

Another idea: maybe add a -h|--help option to the script to show the cli documentation.

andriiryzhkov · 2026-04-29T08:26:37Z

It's a little bit misleading to see my CPU in this line:

Fixed detection.

Also, I'm a little bit confused why it chooses libonnxruntime.so.1.23.2, I thought DT is build with libonnxruntime.so.1.24?

Yes, DT is built and bundled with ONNX Runtime 1.24. But library version we install with this script or UI installation might be different. For AMD it depends on underlying ROCm version - there's only one built ONNX Runtime per specific version of ROCm. For OpenVINO on Intel GPUs, version of ONNX Runtime with GPU support is lagging behind a little bit.

So, ONNX Runtime library with GPU acceleration support might differ from bundled one. It should not cause any problem.

da-phil · 2026-04-29T15:20:17Z

@andriiryzhkov short question: where are you storing the information that a model has been downloaded? I'm asking because I share my darktable configs (darktablerc, library.db, data.db etc.) between two machines (laptop & PC) and on my laptop today, I had the issue that the model was shown as "installed" in the model settings overview, however it couldn't be loaded properly, as my laptop hasn't previously used latest master with the new rawdenoise model, but my PC had yesterday.

andriiryzhkov · 2026-04-29T15:31:32Z

@da-phil : Download status is not stored anywhere, it is resolved at DT start each time from models folder.

da-phil · 2026-04-29T15:34:22Z

@da-phil : Download status is not stored anywhere, it is resolved at DT start each time from models folder.

Thanks for confirming, then this was a different issue. I just deleted the model from the list and re-downloaded successfully.

da-phil · 2026-04-30T19:58:04Z

I think we should merge this PR soon, as this can be really helpful for folks who are willing to test all the new AI features @andriiryzhkov contributed to darktable so far, but need to first install the respective libraries to make it work.
We can surely iron out things with those installation dialogs and scripts as we test and go on master.

andriiryzhkov · 2026-05-01T11:59:55Z

I've split the original scope of this PR into smaller, easier-to-review pieces. After this push, PR #20676 contains only the CLI install scripts and the GPU package registry (tools/ai/install-ort-gpu.{sh,ps1}, tools/ai/install-ort-amd-build.sh, data/ort_gpu.json, plus the new tools/ai/refresh-ort-gpu.py and CI workflow that keeps the registry in sync upstream).

The rest is moving out:

[AI] Add GPU device selection and EP filtering to AI preferences #20905 – AI prefs: GPU device selection and EP filtering. The execution-provider combo now only shows EPs the loaded ORT library actually advertises, and multi-GPU systems get a device picker for CUDA / MIGraphX / DirectML. Already open for review.
(coming soon) AI prefs: in-app install / detect of GPU ORT. The "install" / "detect" buttons on the AI tab that drive the same package registry as the CLI scripts. I'll open this as a separate PR once it's polished – it depends on [AI] Add GPU device selection and EP filtering to AI preferences #20905 landing first since it reuses the EP-filter plumbing.

Splitting like this should make each piece small enough to review on its own. Apologies for the churn – the original PR grew larger than I'd intended.

andriiryzhkov · 2026-05-03T11:23:26Z

@TurboGit : can you check this PR? It has reduced scope now - only additional tools, no changes in C codebase.

TurboGit

Thanks, good to go at this stage.

andriiryzhkov force-pushed the ort_scripts branch 2 times, most recently from 2fc7d22 to bf749a7 Compare April 2, 2026 08:26

andriiryzhkov changed the title ~~[AI] GPU-accelerated ORT install scripts and documentation~~ [AI] GPU ORT install: manifest-driven UI button, scripts, and EP support Apr 2, 2026

andriiryzhkov mentioned this pull request Apr 2, 2026

[AI] Add neural restore lighttable module for AI denoise and upscale #20523

Merged

andriiryzhkov force-pushed the ort_scripts branch 2 times, most recently from 3d4266e to 4544aee Compare April 8, 2026 11:44

andriiryzhkov force-pushed the ort_scripts branch 2 times, most recently from 7810328 to 64815e6 Compare April 11, 2026 16:38

andriiryzhkov force-pushed the ort_scripts branch 4 times, most recently from ee6a76b to 41ad8bb Compare April 16, 2026 15:35

andriiryzhkov marked this pull request as ready for review April 16, 2026 15:36

andriiryzhkov force-pushed the ort_scripts branch from 6adc15d to 5cc84e3 Compare April 23, 2026 13:37

andriiryzhkov force-pushed the ort_scripts branch from 5cc84e3 to fe0d4d9 Compare April 29, 2026 08:18

andriiryzhkov marked this pull request as draft April 30, 2026 18:16

da-phil reviewed Apr 30, 2026

View reviewed changes

Comment thread data/ort_gpu.json Outdated

da-phil reviewed Apr 30, 2026

View reviewed changes

Comment thread data/ort_gpu.json

da-phil reviewed Apr 30, 2026

View reviewed changes

Comment thread tools/ai/install-ort-gpu.sh

andriiryzhkov force-pushed the ort_scripts branch 2 times, most recently from e5aea46 to b512337 Compare May 1, 2026 09:44

andriiryzhkov added 3 commits May 1, 2026 13:08

Add ONNX Runtime GPU install scripts and manifest

718b2e7

Add monthly auto-refresh for ONNX Runtime GPU registry

ead2cdd

Clean stale lib files before install

7cf76ec

andriiryzhkov force-pushed the ort_scripts branch from b512337 to 7cf76ec Compare May 1, 2026 11:46

andriiryzhkov changed the title ~~[AI] GPU ORT install: manifest-driven UI button, scripts, and EP support~~ [AI] GPU ORT install: manifest-driven scripts May 1, 2026

andriiryzhkov marked this pull request as ready for review May 1, 2026 11:58

andriiryzhkov changed the title ~~[AI] GPU ORT install: manifest-driven scripts~~ [AI] GPU acceleration install: manifest-driven scripts May 1, 2026

TurboGit approved these changes May 3, 2026

View reviewed changes

TurboGit merged commit bfc0b56 into darktable-org:master May 3, 2026
5 checks passed

andriiryzhkov deleted the ort_scripts branch May 3, 2026 16:27

Conversation

andriiryzhkov commented Mar 26, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Package manifest (data/ort_gpu.json)

Unified install scripts

Documentation

Uh oh!

andriiryzhkov commented Apr 2, 2026

Uh oh!

TurboGit commented Apr 2, 2026

Uh oh!

andriiryzhkov commented Apr 2, 2026

Uh oh!

TurboGit commented Apr 3, 2026

Uh oh!

andriiryzhkov commented Apr 3, 2026

Uh oh!

TurboGit commented Apr 3, 2026

Uh oh!

andriiryzhkov commented Apr 8, 2026

Uh oh!

da-phil commented Apr 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

andriiryzhkov commented Apr 14, 2026

Uh oh!

da-phil commented Apr 14, 2026

Uh oh!

andriiryzhkov commented Apr 14, 2026

Uh oh!

da-phil commented Apr 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

andriiryzhkov commented Apr 16, 2026

Uh oh!

andriiryzhkov commented Apr 28, 2026

Uh oh!

da-phil commented Apr 28, 2026

Uh oh!

andriiryzhkov commented Apr 29, 2026

Uh oh!

da-phil commented Apr 29, 2026

Uh oh!

andriiryzhkov commented Apr 29, 2026

Uh oh!

da-phil commented Apr 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

da-phil commented Apr 30, 2026

Uh oh!

Uh oh!

Uh oh!

Uh oh!

andriiryzhkov commented May 1, 2026

Uh oh!

andriiryzhkov commented May 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

TurboGit left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

andriiryzhkov commented Mar 26, 2026 •

edited

Loading

Package manifest (`data/ort_gpu.json`)

da-phil commented Apr 14, 2026 •

edited

Loading

da-phil commented Apr 14, 2026 •

edited

Loading

da-phil commented Apr 29, 2026 •

edited

Loading

andriiryzhkov commented May 3, 2026 •

edited

Loading