Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Large Action Model framework to develop AI Web Agents
Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
PRQL is a modern language for transforming data — a simple, powerful, pipelined SQL replacement
Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Multilingual Automatic Speech Recognition with word-level timestamps and confidence