dangxingyu/megakernel-zoo
Resource
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 6 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Collection of LLM decoding engines, each a single persistent GPU kernel built for one specific checkpoint and GPU, written by a coding agent. Includes an OpenAI-compatible server (mkserve), an evaluation suite that checks logits against an FP64 reference, and a kit to build…
Who it's for
CUDA and GPU engineers who run LLM inference on H100 or B200 GPUs and want low-latency single-sequence decoding
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up dangxingyu/megakernel-zoo in my project. Follow its README: https://github.com/dangxingyu/megakernel-zoo. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/dangxingyu/megakernel-zoo?ref=badge)Similar repos
- Veloresearch/kinetic
A Rust inference engine that runs GGUF models, the llama.cpp format, on CPU and on NVIDIA, AMD and Intel GPUs from one binary. It includes speculative decoding and prompt-state reuse for faster genera
- affifuddin-hazam/ghost-infer
A local LLM inference engine in Rust for NVIDIA GPUs that runs GGUF models, serves an OpenAI-compatible API with streaming and tool calls, and includes a Windows desktop app with a chat and file-editi
- Hyperstitioncc/Hyperkernel
Rust implementations of megakernels for NVIDIA B300 GPUs, with host servers for DeepSeek-V4.1-Flash LLM serving, openpilot driving-model inference, Evo 2 7B DNA generation and Matrix-Game 3.0 world-mo
- ekzhang/resin
Experimental Python and Rust library of building blocks for LLM inference engines. Provides a headless Rust scheduler, KV cache and metrics server, where the user writes model-specific forward-pass ke
- eagle-hq/EAGLE-4
Official inference code for EAGLE-4, a speculative decoding system whose drafter adapts its speculation to batch size, hardware and workload. It serves EAGLE-4 drafts on SGLang, vLLM and TokenSpeed th
- ashhart/TensorFold
A Zig inference engine that serves language models on Apple Silicon and NVIDIA GPUs using Metal and CUDA kernels. It reads checkpoints, tokenizes requests and exposes chat, completions, Responses and