Stars
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
A high-throughput and memory-efficient inference and serving engine for LLMs
AI agents running research on single-GPU nanochat training automatically
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
A modular graph-based Retrieval-Augmented Generation (RAG) system
Universal LLM Deployment Engine with ML Compilation
Ongoing research training transformer models at scale
Proxy server to bypass Cloudflare protection
Minimal reproduction of DeepSeek R1-Zero
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Witness the aha moment of VLM with less than $3.
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
Turn detection for full-duplex dialogue communication
LLaMa/RWKV onnx models, quantization and testcase