From a7450ffb80e1ccbb6871bc393931a5810488fa83 Mon Sep 17 00:00:00 2001 From: Timur Rvachov <120140748+trvachov@users.noreply.github.com> Date: Wed, 22 Jan 2025 18:56:27 -0500 Subject: [PATCH] 2.3 (25.01) release notes (#641) ### Description V2.3 release notes. ### Type of changes - [ ] Bug fix (non-breaking change which fixes an issue) - [ ] New feature (non-breaking change which adds functionality) - [ ] Refactor - [x] Documentation update - [ ] Other (please describe): --- docs/docs/user-guide/appendix/releasenotes-fw.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/docs/docs/user-guide/appendix/releasenotes-fw.md b/docs/docs/user-guide/appendix/releasenotes-fw.md index 0079c4b8de..0e376a70c0 100644 --- a/docs/docs/user-guide/appendix/releasenotes-fw.md +++ b/docs/docs/user-guide/appendix/releasenotes-fw.md @@ -1,5 +1,18 @@ # Release Notes +## BioNeMo Framework v2.3 + +### New Features + +* Distributed Inference Support for ESM2 and Geneformer + * Enables linear inference throughput as GPU number is increased + * [See ESM2 inference notebook](https://github.com/NVIDIA/bionemo-framework/blob/release-v2.3/docs/docs/user-guide/examples/bionemo-esm2/inference.ipynb) and use `--num-gpus` parameter. + +### Updates & Improvements + +* Prior Geneformer inference on H100 accuracy regression fixed. +* Base image updated to `nvcr.io/nvidia/pytorch:24.12-py3`; python updated to 3.12 among other core dependency upgrades ([base container release notes here](https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-12.html#rel-24-12)). + ## BioNeMo Framework v2.2 ### New Features