#
Lists (2)
Starred repositories
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without lossing end-to-end metrics across language, image, and video models.
VQVAEs, GumbelSoftmaxes and friends
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
💡 All-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows
Free and open-source map hosting solution with custom styles for websites and apps, using OpenStreetMap data
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
Embedded property graph database built for speed. Vector search and full-text search built in. Implements Cypher.
slime is an LLM post-training framework for RL Scaling.
Lets make video diffusion practical!
Renderer for the harmony response format to be used with gpt-oss
Hierarchical Reasoning Model Official Release
Synthetic data curation for post-training and structured data extraction
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Distributed pushdown cache for DataFusion
The open source developer platform to build AI/LLM applications and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integra…
Build resilient language agents as graphs.
This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for re…
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
Lightweight coding agent that runs in your terminal
The Auron accelerator for distributed computing framework (e.g., Spark) leverages native vectorized execution to accelerate query processing
lossily compress representation vectors using product quantization