#low-latency-inference Repositories
Discover 14 active open source GitHub repositories tagged with #low-latency-inference, accumulating 56,906 total stars (averaging 4,064 stars per project). Leading this topic is alievk/avatarify-python with 16,551 stars.
14 repositories total
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
A fast inference library for running LLMs locally on modern consumer-class GPUs
A lightning fast Finite State machine and REgular expression manipulation library.
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.
โจโจ[NeurIPS 2025] VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
Frequently Asked Questions
What is the most popular #low-latency-inference repository on GitHub?
The top ranked open source #low-latency-inference project on GitHub is alievk/avatarify-python with 16,551 stars. Avatars for Zoom, Skype and other video-conferencing apps.
Which programming languages are most used in #low-latency-inference repositories?
Among the top ranked #low-latency-inference projects on GitHub, the most common programming languages are Python, C++, Cuda.
How is the #low-latency-inference repository ranking calculated?
We track 14 active open source repositories tagged with #low-latency-inference (500+ stars), totaling 56,906 stars with an average of 4,064 stars per repository. Rankings update daily from the GitHub API.