Tag
Announces two open-source Rust projects: Lycan (a graph execution language for contextual bandits) and Syntra (a self-hosted Docker appliance for serving Lycan capsules). The author dogfoods them on a live AI trading product, discovering that data pipeline bugs, not algorithm issues, dominated the adaptation work.
A user shares their setup using two modded RTX 2080 Ti GPUs with 22GB VRAM each to run Qwen 3.6 27B at 38 tokens/s with llama.cpp, including tips on power limiting, tensor split mode, and KV cache settings.
WebHarbor packages 15 real websites (Amazon, GitHub, BBC, etc.) as self-contained Flask+SQLite apps in a single Docker image with sub-second reset, designed for reproducible web agent evaluation and training. The project invites community contributions to expand to 100+ sites, with co-authorship opportunities.
Provides Docker images for running MTP models with llama.cpp, including quantization comparisons and usage instructions.
A user reports an issue where the Qwen 3.6 model stops mid-task when served via vLLM with specific Docker and speculative decoding configurations.
An explanatory article detailing how BusyBox functions as a multi-call binary in Alpine Linux, providing a single executable for various command-line utilities through symlinks and applet configuration.
Aerol AI has open-sourced a MicroVM runtime compatible with Docker and gVisor sandboxes, offering faster setup and launch times than existing solutions.
TrendRadar is an open-source hot-topic aggregator that uses AI to filter content based on interests and generate briefings, supporting Docker deployment and multi-platform notifications.
This is a Hacker News community thread where developers share their current projects, including a Docker image optimizer called Clipper, a continual learning transformer adaptation named RVW, a ranking app called Rankr, and an AI deep research tool called Webhound.
The author compares the compact 35MB size of a WebAssembly-compiled Godot game engine to typical Docker base images, questioning why WASM adoption remains limited despite its significant size and deployment advantages.
A new method for orchestrating agents is being worked on, featuring delegation plans and subagents that can run locally or in Dockerized cloud environments, with message passing between them.
This article introduces 7 production-ready skills from the Hermes Skills Hub, covering the full lifecycle from tool integration and structured output to deployment, observability, and security.
Arch Linux released a bit-for-bit reproducible Docker image under a new "repro" tag, requiring users to regenerate pacman keys before package management.
Intel’s LLM-Scaler vllm-0.14.0-b8.2 adds official support for the Arc Pro B70 GPU, enabling Docker-based large-model inference on Battlemage hardware.
GoModel is a new open-source AI gateway written in Go that offers a unified OpenAI-compatible API for multiple providers and claims to be 44× lighter than LiteLLM.
AutoDev is an AI-driven software development framework that automates complex engineering tasks, such as code and test generation, within a secure Docker environment. It achieves high performance on the HumanEval dataset by enabling autonomous planning and execution of intricate software engineering tasks.
OpenAI shares infrastructure lessons from scaling Kubernetes to 2,500 nodes, detailing optimizations for container image pulls including kubelet configuration changes, Docker overlay2 migration, and preloading strategies to resolve Pending pod issues.