Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
- ai
- ai-interpretability
- ai-safety
- aisafety
132,241 visible repositories in the index
673–696 of 748 · Most stars
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
🏹 Parse JSON with style
SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers and PyTorch.
[MIRROR] unofficial implementation of Dante protocol (Audio over IP)
High-performance Bayesian Data Analysis on the GPU in Clojure
Inference module for RangeNet++ (milioto2019iros, chen2019iros)
Python package facilitating the use of Bayesian Deep Learning methods with Variational Inference for PyTorch
A fast and efficient type assistant for Python, including tensor shape inference
Local-first engineering agent that deploys, benchmarks and tunes vLLM/SGLang inference services on your own GPUs, with auditable run evidence.
Bayesian Generalized Kernel Inference for Terrain Traversability Mapping
The example project of inferencing Semantic Segementation using Core ML
This repository provides you with an easy-to-use labeling tool for State-of-the-art Deep Learning training purposes. It supports Auto-Labeling.
C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer
Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how that access is handed off.
Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.
Our lightning-fast inference engine.
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
A distributed Spark/Scala implementation of the isolation forest and extended isolation forest algorithms for unsupervised outlier detection, featuring support for scalable training and ONNX export for easy cross-platform inference.
TypeQL: Built for systems, not records
Fast local LLM inference for the GPU you already have: one Rust binary, GGUF models, an OpenAI-compatible server and a chat page with a ghost.
A library and microservice implementing the health and care terminology SNOMED CT with support for cross-maps, inference, fast full-text search, autocompletion, compositional grammar and the expression constraint language.
Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a switchless three-node or four-node DGX Spark fabric.
small LLM inference engine from scratch, w/ 6+ hours of youtube tutorials & 85+ pages of handwritten notes included