Lists (14)
Starred repositories
Causal depthwise conv1d in CUDA, with a PyTorch interface
The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription
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…
Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.
📰 Must-read papers on KV Cache Compression (constantly updating 🤗).
Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
Fast and memory-efficient exact attention
Text-audio foundation model from Boson AI
vineyard (v6d): an in-memory immutable data manager. (Project under CNCF, TAG-Storage)
CUDA Templates and Python DSLs for High-Performance Linear Algebra
Added vLLM support to IndexTTS for faster inference.
A TTS model capable of generating ultra-realistic dialogue in one pass.
ClickHouse® is a real-time analytics database management system
Fully open reproduction of DeepSeek-R1
🔥中文 prompt 精选🔥，ChatGPT 使用指南，提升 ChatGPT 可玩性和可用性！🚀
A free weekly newsletter featuring noteworthy articles, tutorials, open-source projects, podcasts, videos, trending topics, and more.Python 潮流周刊，分享文章、教程、开源项目、软件工具、播客和视频、热门话题等内容。
Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."