Four reproducible parser failures in vLLM 0.26.0, 0.27.1, and 0.28.0 can drop or garble tool calls and reasoning content while still returning HTTP 200, according to the Ingot team's tests on CPU with…
Ornith-1.5, a family of open-weight foundation models built on Qwen3.5 and Gemma4, trains through a self-improvement loop that jointly generates tasks, constructs scaffolds, and runs reinforcement lea…
Baidu's vLLM Kunlun plugin, open-sourced on Dec 8, 2025, enables vLLM to run on Kunlun XPU hardware, supporting 20+ models including Qwen, Llama, DeepSeek, GLM, and Gemma4, with features like quantiza…
A developer building a local-first infrastructure monitoring agent with PicoClaw encountered an undocumented Ollama bug where the 'think' parameter is not supported in Modelfile syntax, forcing a work…
Honeycomb processes 2 million agent-initiated query runs per month, up from a $0.60 eight-tool-call demo a year ago, with average tool calls per session doubling between February and June, according t…
Open-source coding agents can now run entirely on local consumer hardware such as a 2020-era NVIDIA RTX 3090, eliminating usage-based pricing from AI vendors. The setup uses a quantized Gemma4 model s…
Llambda.lisp, a pure Common Lisp inference engine for running quantized large language models from .gguf files, achieves C-level throughput using AVX2/FMA acceleration and multi-threading without wrap…
NVIDIA Research released SpatialClaw, a training-free framework that uses code as the action interface for spatial reasoning in vision-language models. The framework achieves 59.9% average accuracy ac…
Ollama 0.3.0 introduced a format parameter that enforces structured JSON output from local LLMs via constrained decoding, eliminating parsing failures caused by markdown wrappers or extraneous text. T…
Researchers at Stanford University and Lambda Labs released OpenJarvis, an open-source framework that runs AI inference, agents, memory, and learning entirely on-device. The framework achieves perform…
A developer has shared a complete setup guide for running a local AI Retrieval Augmented Generation (RAG) system using free, open-source tools. The configuration uses Ollama to run Google's Gemma4 mod…
This article details a Retrieval-Augmented Generation (RAG) architecture built on AWS EC2 that uses n8n for workflow orchestration, PostgreSQL with pgvector for vector storage, and Ollama to run the G…
The GGUF file format consolidates all necessary model components—including weights, chat templates, and special tokens—into a single file, offering a more ergonomic alternative to the scattered JSON f…