Lesheng Jin's repositories
FastChat
The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"
mlc-llm
Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
models
Models and examples built with TensorFlow
relax
Temp repo for prototyping relax(relay next), the effort will be upstreamed. We use the wiki pages on this repo to host design docs.
tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
CTranslate2
Fast inference engine for Transformer models
faster-whisper
Faster Whisper transcription with CTranslate2
libflash_attn
Standalone Flash Attention v2 kernel without libtorch dependency
web-llm
Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.
whisper-jax
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)