v26.01.00

This is a beta release of Legate.

Pip wheels are available on PyPI at https://pypi.org/project/legate/, for Linux (x86-64 and ARM64, with CUDA 12 and multi-node support) and macOS (for ARM64). Conda packages are available at https://anaconda.org/legate/legate, for Linux (x86-64 and ARM64, with CUDA 12/13 and multi-node support). GASNet-based (rather than UCX-based) conda packages are under the gex label. Windows is currently supported through WSL.

Documentation for this release can be found at https://docs.nvidia.com/legate/26.01/.

Highlights

Streaming / auto-batching

• Add a safety checker, that identifies conditions that prevent a series of operations from being executed in "batches" (e.g. non-pointwise dependencies between two operations).

Memory management

• Fix a bug that would prevent the reuse of an instance covering the full Store, when attempting to create an allocation for a partial slice.
• Report base address of instances taking up memory in OOM messages, to make it easier to diagnose e.g. memory fragmentation.

Documentation

• Add an HDF5 write benchmark.

Packaging

• Pin the legate-profiler conda package to the main legate package it aligns with, to ensure a consistent environment.
• Bump to top-of-tree Legion, to include latest performance improvements and bugfixes.

Known issues

• As of October 2025, the GASNet wrapper on Perlmutter only works when the NERSC-provided mpich module is loaded. Attempts to build or use the wrapper with cray-mpich currently fail, so make sure module load mpich is issued before running build-gex-wrapper.sh.
• As of October 2025, Perlmutter jobs that request more than 32 GB of device memory (for example, --fbmem 64000) must include REALM_DEFAULT_ARGS='-gex:bindcuda 0'. Otherwise the OFI provider aborts with Unexpected error 12 (Cannot allocate memory) from fi_mr_regattr().

Full Changelog: https://docs.nvidia.com/legate/latest/changes/2601.html, v25.11.00...v26.01.00