imagem 24

Ollama v0.32.3-rc0: Refinements for MLX, GLM Tools, and Model Alignments

Leave a Comment / AI & Machine Learning /

The latest release candidate of Ollama, v0.32.3-rc0, arrives with a focused set of refinements that strengthen the platform’s stability and polish for self-hosted AI users. Rather than introducing flashy new features, this update fine-tunes existing components to ensure a smoother, more reliable experience. Owners of Apple Silicon machines will appreciate the MLX backend update, which […]

Ollama v0.32.3-rc0: Refinements for MLX, GLM Tools, and Model Alignments Read More »

imagem 23

Jellyfin Server 12.0 RC3 Preview: Performance Polish and Key Fixes

Leave a Comment / Self-Hosted & Containers /

Jellyfin Server 12.0 RC3 Arrives as a Critical Preview Update The Jellyfin team has rolled out the third release candidate for the upcoming 12.0 server version, inviting testers to help squash bugs before the final launch. As always, they strongly recommend backing up your server before upgrading, especially given this pre-release status. A Fresh Versioning

Jellyfin Server 12.0 RC3 Preview: Performance Polish and Key Fixes Read More »

imagem 21

LangChain-Anthropic 1.5.0: New Reasoning Control and Tool Recognition Fix

Leave a Comment / AI & Machine Learning /

The latest update to the LangChain-Anthropic integration, version 1.5.0, brings a notable new feature and important fixes for self-hosted users. This release focuses on enhancing model controllability and ensuring smoother tool interactions. Reasoning Effort Control: A new standard parameter, reasoning_effort, has been added to chat models. This allows developers to adjust the depth of reasoning

LangChain-Anthropic 1.5.0: New Reasoning Control and Tool Recognition Fix Read More »

imagem 20

llama-arch Fixes DeepSeek4 APE Tensor Operation for Improved Model Compatibility

Leave a Comment / AI & Machine Learning /

A recent update to llama-arch, a core component of the llamacpp inference engine, addresses a critical bug affecting the APE (Adaptive Positional Encoding) tensor operation used in DeepSeek4 models. This fix ensures accurate computation during model inference, which is essential for developers running DeepSeek4 on self-hosted environments. By resolving this issue, llama-arch improves compatibility and

llama-arch Fixes DeepSeek4 APE Tensor Operation for Improved Model Compatibility Read More »

imagem 19

Ollama v0.32.2-rc0 Release: Agent Upgrades, Backend Updates, and Build Improvements

Leave a Comment / AI & Machine Learning /

This release candidate brings significant enhancements to the agent system, including a new skills system that allows more flexible tool usage. Agent semantics and user experience have been cleaned up, removing dead code and improving the handling of slash commands—commands are now completed before being submitted. The terminal interface now renders bold emphasis consistently across

Ollama v0.32.2-rc0 Release: Agent Upgrades, Backend Updates, and Build Improvements Read More »

imagem 18

Delayed Home Assistant Release Delivers a Slew of Fixes and Integration Updates

Leave a Comment / Automation & IoT /

The latest Home Assistant release experienced an unexpected delay—it was originally slated to ship last Friday, but technical difficulties threw a wrench in the works. The team sincerely apologizes for the slower pace and thanks everyone for their patience. Roborock vacuum owners will appreciate a series of updates aimed at ironing out kinks. The underlying

Delayed Home Assistant Release Delivers a Slew of Fixes and Integration Updates Read More »

imagem 17

Traefik Patch Release Fixes Security Flaw and Critical Middleware Bugs

Leave a Comment / Self-Hosted & Containers /

This Traefik release addresses an important security vulnerability (CVE) and brings stability improvements for users, particularly those running Kubernetes. A patch has been applied to resolve the issue detailed in advisory GHSA-8rxv-jg7p-wvg3, ensuring a safer default configuration. Several bug fixes target middleware and Kubernetes integrations. A missing field in the ErrorRequestHeaders for CRDs has been

Traefik Patch Release Fixes Security Flaw and Critical Middleware Bugs Read More »

imagem 16

Portainer Update Resolves Regression, Boosts Edge Reliability, and Patches Vulnerabilities

Leave a Comment / Self-Hosted & Containers /

Known Issues In async Edge environments, browsing a snapshot may display an invalid update schedule date. Known Issues with Podman Support Podman environments are not supported by the auto-onboarding script. Adding Podman environments via socket while running a Portainer server on Docker (and vice versa) is not possible. Support is limited to CentOS 9 with

Portainer Update Resolves Regression, Boosts Edge Reliability, and Patches Vulnerabilities Read More »

imagem 15

🚀 Jellyfin Server 12.0 RC2 Release Preview

Leave a Comment / Self-Hosted & Containers /

We’re excited to unveil the second release candidate for Jellyfin 12.0! As a preview release, this is aimed at testers who want to help squash bugs before the final launch. Your help in finding issues is invaluable. As always, please stop your Jellyfin server and take a complete backup before upgrading. A note about versioning

🚀 Jellyfin Server 12.0 RC2 Release Preview Read More »

RSS FEED
RSS FEED