#paged-attention Repositories
Discover 6 active open source GitHub repositories tagged with #paged-attention, accumulating 9,822 total stars (averaging 1,637 stars per project). Leading this topic is xlite-dev/Awesome-LLM-Inference with 5,565 stars.
6 repositories total
๐A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.๐
Pure Rust + CUDA LLM inference engine โ no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
From teacher to tiles โ a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.
Frequently Asked Questions
What is the most popular #paged-attention repository on GitHub?
The top ranked open source #paged-attention project on GitHub is xlite-dev/Awesome-LLM-Inference with 5,565 stars. ๐A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.๐
Which programming languages are most used in #paged-attention repositories?
Among the top ranked #paged-attention projects on GitHub, the most common programming languages are Python, Rust.
How is the #paged-attention repository ranking calculated?
We track 6 active open source repositories tagged with #paged-attention (500+ stars), totaling 9,822 stars with an average of 1,637 stars per repository. Rankings update daily from the GitHub API.