Models & Labs
GitHub Copilot Deprecates GPT-4.1 Model
GitHub Changeloghigh confidence
Why it matters
- →Deprecation of GPT-4.1 indicates a shift towards newer AI models in GitHub Copilot.
- →Users must adapt their workflows to ensure compatibility with supported models.
- →This change may improve efficiency and performance in AI-assisted coding tools.
GitHub has deprecated the GPT-4.1 model in all Copilot experiences, effective June 1, 2026. Users must update their workflows to use supported models, and administrators should enable access to these alternatives in Copilot settings. This change affects Copilot Chat, inline edits, and code completions. GitHub Enterprise customers are advised to contact their account managers for assistance. The deprecation suggests a strategic shift towards newer models, and users are encouraged to review GitHub's documentation for further guidance.
Read originalMore from GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Copilot Enhancements in VS Code May Releases
GitHub's latest updates to Visual Studio Code bring a significant shift towards an agent-first experience, allowing developers to focus on task completion rather than just code editing. The introduction of the Agents window in preview mode facilitates faster navigation and change review across multiple projects. Notably, the updates also enhance support for remote agent sessions, enabling them to continue even when disconnected. These changes, along with expanded BYOK model support and improved session synchronization, mark a step forward in making VS Code a more integrated and efficient development environment.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Copilot App Expands Technical Preview
GitHub has expanded the technical preview of its Copilot app to all existing Copilot Pro, Pro+, Business, and Enterprise customers, marking a significant step in agent-native software development. The app introduces 'canvases', a new feature that allows users to interact with and verify agent work in real-time, enhancing collaboration between humans and AI agents. This release shifts the focus from traditional coding to managing and steering agent output, offering a more integrated development experience. With features like voice conversations and cloud sessions, the Copilot app aims to streamline the development process by making agent interactions more visible and actionable.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Copilot SDK Now Generally Available
GitHub has made its Copilot SDK generally available, allowing developers to integrate Copilot's agentic engine into their applications with a stable API. This release means developers can now access the same runtime that powers GitHub Copilot, enabling features like planning, tool invocation, and multi-turn sessions without building their own orchestration layers. The SDK supports multiple programming languages, including a new Java integration, and offers features like OpenTelemetry tracing and flexible authentication. This marks a significant step in making AI-driven development tools more accessible and customizable for developers.
GitHub Changelog
More in Models & Labs
Models & Labsmodels
v0.22.1rc2 resolves CUTLASS fmin issue
The v0.22.1rc2 release addresses a specific compatibility issue with CUTLASS fmin, crucial for initializing DeepSeek-V4. This fix ensures smoother integration and functionality for developers relying on this setup. While it may seem like a minor update, resolving such compatibility issues can significantly enhance the reliability and performance of AI models. This update is particularly relevant for developers working with the DeepSeek-V4 model, ensuring they can proceed without encountering initialization errors.
vLLM Releases
Models & Labsmodels
llama.cpp b9491 release addresses PDL race conditions
The b9491 release of llama.cpp resolves PDL race conditions by eliminating 'restrict' from PDL kernel headers, which were previously causing compatibility issues. This update introduces preprocessor directives to ensure performance is maintained on older architectures while simplifying the use of 'restrict' through macros. Additionally, the release addresses the PDL restrict issue on Hopper architectures. These changes are crucial for developers as they enhance compatibility and performance across different operating systems and hardware configurations, making llama.cpp more robust and versatile.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b9498 Release Enhances RVV Quantization
The b9498 release of llama.cpp significantly boosts RVV quantization by extending vector dot operations to higher VLENs. This update introduces new 512b and 1024b implementations for quantization schemes like iq4_xs and q6_K, enhancing performance on targeted architectures. While no new models are introduced, the release focuses on refining existing functionalities, particularly for CPU and GPU tasks. With support for macOS, Linux, Windows, and openEuler, llama.cpp becomes a more adaptable tool for developers working with a range of hardware setups. This update underscores llama.cpp's commitment to optimizing performance across different environments.
llama.cpp Releases