NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.
An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more
OpenFE: automated feature generation with expert-level performance
LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.
sbi is a Python package for simulation-based inference, designed to meet the needs of both researchers and practitioners. Whether you need fine-grained control or an easy-to-use interface, sbi has you covered.
- simulation-based-inference
- likelihood-free-inference
- bayesian-inference
- parameter-estimation
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference
Phylogenetic orthology inference for comparative genomics
- gene-trees
- orthogroup
- orthologs
- gene-duplication
This repository contains tutorials and examples for Triton Inference Server
Python Computer Vision & Video Analytics Framework With Batteries Included
The repository host gives no description.
Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"
Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.
The repository host gives no description.
Remory: Learning Residual Memory for Context Compaction
- context-compaction
- inference
- llm-agents
- residual-memory
Ontology-Augmented Generation for AI agents.
Translated斑海豹 (Spotted Seal) — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions.
- bilingual
- calibration
- cpu-inference
- decision-making
Official Hi3D v1.0: high-resolution 3D geometry refinement built on Sparc3D. Inference code, model weights, and documentation.
- 3d-generation
- image-to-3d
- geometry-refinement
- sparc3d
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
🔥🔥 The extremely fast inference engine for decision model
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
- pytorch
- semantic-segmentation
- cityscape-dataset
- lednet
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