torch

This release includes numerous Studio and Desktop improvements, bug fixes, and feature enhancements. Key updates involve better handling of cached pipelines, improved UI elements in Studio, and more robust desktop application behavior.

This release introduces support for the new Gemma 4 12B model and significantly enhances Unsloth Studio with MCP live tools, Projects, and an experimental Canvas for interactive HTML artifacts. Installation methods have been updated, and numerous runtime fixes address CUDA compatibility across Windows, Linux, and ARM64.

vLLM 0.10.2 introduces native aarch64 support, PyTorch 2.8.0 integration, and extensive optimizations for NVIDIA Blackwell GPUs. It expands model support to include Whisper and various vision-language models while maturing the V1 engine core.

vLLM v0.7.0 upgrades to PyTorch 2.7 and CUDA 12.8, introducing initial NVIDIA Blackwell support and advanced scaling features like Expert and Data Parallelism. It also includes significant model expansions, a migration to MkDocs, and a shift to deterministic defaults for the V1 engine.

This minor release introduces quality-of-life improvements, notably enhanced Canvas color controls and default LoRA weight settings, alongside numerous bug fixes across the UI and internal organization.

This release introduces several new features, including support for async node functions and a reconstructed SA-Solver, alongside numerous bug fixes addressing issues in training, API polling, and various node operations. The release also cleans up old code and improves compatibility.

A patch release addressing minor bugs in hub kernels, remote code, and specific model implementations like Chameleon and PyTorch deformable attention.