Stars
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
A lightweight data processing framework built on DuckDB and 3FS.
FlashInfer: Kernel Library for LLM Serving
A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
Cost-efficient and pluggable Infrastructure components for GenAI inference
Ongoing research training transformer models at scale
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Fast and memory-efficient exact attention
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
Fully open reproduction of DeepSeek-R1
Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…
Dynamic Memory Management for Serving LLMs without PagedAttention
Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.
A high-throughput and memory-efficient inference and serving engine for LLMs
[NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations".
Out-of-distribution detection, robustness, and generalization resources. The repository contains a curated list of papers, tutorials, books, videos, articles and open-source libraries etc
A quick guide (especially) for trending instruction finetuning datasets
Object Recognition as Next Token Prediction (CVPR 2024 Highlight)
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
A curated list of awesome open-source libraries for production LLM
A collection of design patterns/idioms in Python
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Repository of Transformer based PyTorch Time Series Models
AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation