AI & Machine Learning

imagem 40

Ollama v0.32.5 Fixes NVFP4 Output Quality Bug on Apple Silicon

Leave a Comment / AI & Machine Learning /

Ollama v0.32.5 Release Notes The latest point release, Ollama v0.32.5, resolves a significant bug affecting users running NVFP4‑based models such as Laguna on Apple Silicon Macs. A flaw in the MLX Metal backend could previously degrade output quality, leading to less accurate or lower‑fidelity responses from these models. With the fix in place, self‑hosted users […]

Ollama v0.32.5 Fixes NVFP4 Output Quality Bug on Apple Silicon Read More »

imagem 39

AWS Weekly Roundup: Local Zone in Athens, Claude Opus 5 on AWS, Lambda durable execution for .NET, and more (July 27, 2026)

Leave a Comment / AI & Machine Learning /

Last week, I had the privilege of spending three days in São Paulo with technical builders from across Latin America at a regional tech event brimming with deep-dive sessions, hands-on workshops, and conversations with customers and partners. What stood out wasn’t any single session—it was the palpable energy of a tech community that rarely gets

AWS Weekly Roundup: Local Zone in Athens, Claude Opus 5 on AWS, Lambda durable execution for .NET, and more (July 27, 2026) Read More »

imagem 37

Llama.cpp Build b10149 Released with Test Suite Refinement and Cross-Platform Binaries

Leave a Comment / AI & Machine Learning /

The latest llama.cpp release, build b10149, has arrived, bringing a modest but meaningful enhancement to the project’s testing infrastructure. The primary change in this version removes an unnecessary synchronization call from the test-save-load-state procedure. While this adjustment doesn’t alter the core functionality for end users, it tidies up the codebase and may contribute to more

Llama.cpp Build b10149 Released with Test Suite Refinement and Cross-Platform Binaries Read More »

imagem 35

Ollama v0.32.5-rc0 Released with MLX Update

Leave a Comment / AI & Machine Learning /

The latest release candidate of Ollama, version 0.32.5-rc0, brings an update to the MLX backend. This improvement enhances compatibility and performance for users running Ollama on Apple Silicon hardware. Self-hosted users can expect better integration with the latest MLX features, ensuring a smoother inference experience. As a pre-release, it’s an opportunity to test the updated

Ollama v0.32.5-rc0 Released with MLX Update Read More »

imagem 34

Ollama 0.32.4 Brings Laguna to Apple GPUs, Speeds Up Qwen3 MoE, and Refines Speculative Decoding

Leave a Comment / AI & Machine Learning /

The latest point release of Ollama, version 0.32.4, expands hardware support by enabling the Laguna model series on Apple GPUs through the MLX engine. This means self-hosted users with Apple Silicon can now run these models with full hardware acceleration, tapping into the performance and efficiency of the Metal-backed MLX runtime that has already proven

Ollama 0.32.4 Brings Laguna to Apple GPUs, Speeds Up Qwen3 MoE, and Refines Speculative Decoding Read More »

imagem 31

LangChain-OpenAI v1.4.1: LangSmith Gateway Support and Model Profile Fix

Leave a Comment / AI & Machine Learning /

LangChain-OpenAI version 1.4.1 is a minor release that builds on the previous 1.4.0 with a couple of practical improvements. It focuses on better integration with LangSmith’s infrastructure and correcting a model configuration quirk. A notable new feature is the ability to route API calls through LangSmith’s gateway by simply setting an environment variable. This makes

LangChain-OpenAI v1.4.1: LangSmith Gateway Support and Model Profile Fix Read More »

imagem 30

Ollama v0.32.3: Smooth Downloads, Expanded GPU Support, and Laguna 2.1 Integration

Leave a Comment / AI & Machine Learning /

The latest Ollama update fixes a frustrating bug where model downloads would stall before sending any data. It also resolves an issue with GLM tool calls being silently dropped at the end of generation, ensuring that tool interactions are reliable. Integration improvements include the restoration of Claude Code Channels and a fix for Anthropic thinking

Ollama v0.32.3: Smooth Downloads, Expanded GPU Support, and Laguna 2.1 Integration Read More »

imagem 26

LangChain-OpenRouter 0.2.7 Keeps Model Profiles and Dependencies Current

Leave a Comment / AI & Machine Learning /

The langchain-openrouter package has been updated to version 0.2.7, bringing a wave of routine but essential syncs that keep your self-hosted setup aligned with the latest OpenRouter offerings. Central to this release are multiple refreshes of model profile data — the internal catalog that describes which models are available, their capabilities, and how to interact

LangChain-OpenRouter 0.2.7 Keeps Model Profiles and Dependencies Current Read More »

imagem 25

Metal Backend Adds Half-Precision Support for Leaky ReLU

Leave a Comment / AI & Machine Learning /

The latest update to the Metal backend extends Leaky ReLU activation with support for half-precision (f16) floating-point data. This enables efficient computation and reduced memory usage when running models on Apple GPUs, particularly benefiting inference tasks where lower precision is acceptable. Users leveraging Metal acceleration can now take advantage of faster matrix operations without sacrificing

Metal Backend Adds Half-Precision Support for Leaky ReLU Read More »

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 »

RSS FEED
RSS FEED