v0.6.4

[0.6.4] - 2026-03-02

• bugfix: correct wrong input token creation in feature extraction for models with eos tokens.

v0.6.3

[0.6.3] - 2026-02-26

Changed

• Upgraded to ORT GenAI v0.12.0
• Upgraded to ORT v1.24.2
• Upgraded to Go v1.26.0
• Upgraded tokenizers to v1.25.0
• Added WithLogSeverityLevel, WithEnvLoggingLevel, WithGraphOptimizationLevel and WithExtraExecutionProvider options
• Separated TensorRT and NvTensorRTRTX
• Memory usage and bugfixes to generative pipelines

v0.6.2

First release of 2026!

Changed

• Added TabularPipeline to run onnx exports of classical ML models (regression or classification) from, e.g., sklearn
• Added multimodal support for text generation pipeline (kudos to @ajroetker)
• Memory mapped loading of onnx models on native fs to reduce memory usage

Full Changelog: v0.6.1...v0.6.2

v0.6.1 🌲❄️🎄🎁 - 2025-12-23

Changed

• Explicit GoMLX compilation cache control via WithGoMLXBatchBuckets and WithGoMLXSequenceBuckets.
• Finalize device memory earlier in XLA sessions, reducing memory pressure when using TPU/GPU.
• Tokenizer can handle/ignore additional image tensor types.
• Allow 4D dimensions for multimodal featureExtraction pipelines.
• Allow multiple ONNX files/models to load from the same model directory.
• Restore support for GLIBC 2.34 in XLA
• Also disable XLA dependency autoinstall in training mode (will implement global C dependency autoinstall in near future!)

v0.6.0 🌲❄️🎄🎁 - 2025-12-18

Changed

• Integrated ONNX Runtime GenAI backend for significantly faster generative inference and broad model support.
• Added ObjectDetection pipeline
• Added WithTPU option to NewXLASession
• FeatureExtractionPipeline now supports image inputs, enabling vision models like CLIP
• Updated Onnx Runtime to 1.23.2, and GoMLX to 0.26.0

Breaking changes

• ORT Gen AI has strong requirements on the name of the base ORT library. It should not be renamed from the release zip (e.g. libonnxruntime.so)
• WithOnnxLibraryPath should now be the folder contining the ORT library. The library name is now inferred from the current operating system.
• XLA now uses go-xla to manage PJRT dependencies, see our Dockerfile for details

Fixed

• Model loading path could potentially duplicate paths (thanks @ajroetker)

New Contributors

• @ajroetker made their first contribution in #102

Full Changelog: v0.5.10...v0.6.0

v0.5.10

[0.5.10] - 2025-12-08

Breaking changes

• breaking: GetStatistics on a session returns a map of pipeline name to statistics object

v0.5.9

[0.5.9] - 2025-12-08

Breaking changes

• breaking: GetStatistics now returns a Statistics struct for the pipelines rather than a list of strings
• breaking: pipelineBackends has been renamed to backends

Changes

• update of onnxruntime_go, goMLX, gopjrt

Improvements

• support splitIntoWords for tokenClassificationPipeline

v0.5.8

[0.5.8] - 2025-11-22

Changed

• Support models that do not utilize attention masks in FeatureExtractionPipeline
• Bump onnx-gomlx to v0.3.2 for expanded model support in Go sessions.

New Contributors

• @lairdm made their first contribution in #95

v0.5.7

[0.5.7] - 2025-11-11

Changed

• Update Go, Tokenizers, OnnxRuntime and GoMLX dependencies
• Compatibility with NHWC and NCHW formats in Image Classification Pipeline

v0.5.6

• Update to new goMLX project structure (0.24.0+)
• remove the depency on python when installing goMLX libraries