Stars
⚡ Fastest way to serve open source ML models to millions
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
Ongoing research training transformer models at scale
A PyTorch native platform for training generative AI models
A library to capture canvas-based animations at a fixed framerate
Receives canvas frames from browser to generate video on the server. Compatible with CCapture.js
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
F Lite is a 10B parameter diffusion model created by Freepik and Fal, trained exclusively on copyright-safe and SFW content.
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
A high-throughput and memory-efficient inference and serving engine for LLMs
This is the documentation repository for SGLang. It is auto-generated from https://github.com/sgl-project/sglang/tree/main/docs.
The JavaScript client and utilities to fal-serverless with built-in TypeScript definitions
Extended pickling support for Python objects
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
🍏 + 🎯 + 🐍 = Query Apple's FindMy Network with Python!
Kyanos is a networking analysis tool using eBPF. It can visualize the time packets spend in the kernel, capture requests/responses, makes troubleshooting more efficient.
[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
A Data Streaming Library for Efficient Neural Network Training
A feature-rich command-line audio/video downloader