aboutsummaryrefslogtreecommitdiffstats
path: root/model-integration/src/main/java/ai/vespa/modelintegration/evaluator/OnnxEvaluator.java
Commit message (Collapse)AuthorAgeFilesLines
* Less verbose logging when failing to find CUDA and it is optionalJo Kristian Bergum2023-10-261-2/+2
|
* Update copyrightJon Bratseth2023-10-091-1/+1
|
* Log when GPU configuration is successfulMartin Polden2023-07-191-3/+8
|
* Log warning when failing to use GPUMartin Polden2023-07-191-1/+6
|
* Support loading ONNX models through byte arrayBjørn Christian Seime2023-03-301-5/+14
| | | | Rewrite OnnxRuntimeTest to test through it's public API
* Replace `OnnxEvaluatorCache` with OnnxRuntimeBjørn Christian Seime2023-02-271-49/+19
| | | | | | Require an `OnnxRuntime` instance to create `OnnxEvaluator` instances. Cache underlying `OrtSession` instead of `OnnxEvaluator`. Move static helpers for checking Onnx runtime availability from `OnnxEvaluator` to `OnnxRuntime`.
* handle non-identifier onnx input/output names: instead of the conflictingArne Juul2023-02-221-0/+30
| | | | | ad-hoc code in OnnxEvaluator, do it as part of general input/output mapping in OnnxModel.
* Make OnnxEvaluator closableBjørn Christian Seime2023-02-221-1/+12
|
* ensure outputs with names as promised by getOutputInfo()Arne Juul2023-02-101-1/+21
|
* Fix GPU detectionMartin Polden2023-02-091-1/+1
|
* Allow fallback to CPU if nodes are provisioned without GPUMartin Polden2023-02-081-4/+8
|
* Remove 'required' attributeMartin Polden2023-01-261-6/+5
|
* Skip CUDA entirely if GPU device is optionalMartin Polden2023-01-261-12/+28
| | | | CUDA may fail after its library is loaded, e.g. when the session is created.
* trying to make an OnnxEvaluator with empty path would failArne Juul2022-12-121-0/+8
|
* Skip test if onnx is not available (arm64)Lester Solbakken2022-04-011-1/+5
|
* Move method for checking if onnxruntime is availableHarald Musum2022-02-111-0/+9
| | | | Use it in model-evaluation as well
* Update Verizon Media copyright notices.gjoranv2021-10-071-1/+1
|
* Add parsing of ONNX Runtime session options to services.xmlLester Solbakken2021-09-301-6/+8
|
* Set default session options for ONNX-RT stateless evalLester Solbakken2021-09-141-0/+3
|
* Set max optimization level for onnx runtime model evaluation in containerLester Solbakken2021-09-091-1/+3
|
* Excplicity close native onnx tensors used as inputLester Solbakken2021-08-201-2/+12
|
* Revert "Revert "Add ONNX-RT evaluator to model-integration module""Lester Solbakken2021-05-191-0/+79
| | | | This reverts commit 97080252fac0ba45b58f9d0efb56603da518428f.
* Revert "Add ONNX-RT evaluator to model-integration module"Lester Solbakken2021-05-191-79/+0
|
* Add ONNX-RT evaluator to model-integration moduleLester Solbakken2021-05-191-0/+79