An open-source Photograph travel Blog📸built using Next.js, Drizzle, Neon, Better auth, Shadcn/ui and tRPC.

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

FlashMLA: Efficient MLA decoding kernels

DeepEP: an efficient expert-parallel communication library

Fully open reproduction of DeepSeek-R1

Utility to manage SSH public keys stored in LDAP.

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Chat with Lex! A RAG app, using HyDE with milvus DB for vector store, VLLM for LLM inference, and FastEmbed for Embeddings!

Efficient Triton Kernels for LLM Training

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Machine Learning Engineering Open Book

ROS2 Project involving 2d and 3d mapping of environment

Python Dynamic Mode Decomposition

Open Neural Network Exchange to C compiler.

A high-throughput and memory-efficient inference and serving engine for LLMs

A Gradio web UI for Large Language Models with support for multiple inference backends.

A repository for hacking Generative Fill with Open Source Tools

High-speed Large Language Model Serving for Local Deployment

This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu , Terra Blevins…

A framework for few-shot evaluation of language models.

DiffusionFastForward: a free course and experimental framework for diffusion-based generative models

ComfyUI custom nodes for inpainting/outpainting using the new latent consistency model (LCM)

SD.Next: All-in-one for AI generative image

Dynamic Resource Allocation (DRA) for NVIDIA GPUs in Kubernetes

ML model optimization product to accelerate inference.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.