lucebox

Repository facts

Stars

2,928

Forks

286

Open issues and pull requests

101

Primary language

C++

License

Apache License 2.0 (Apache-2.0)

Owner

Luce-Org · Organization

Created

Apr 3, 2026

Last push

Oct 18, 2026

Topics

• cuda
• cuda-kernels
• dflash
• heterogeneous-computing
• kernel
• llama-cpp
• local-ai
• luce
• megakernel
• pflash
• poolside
• qwen
• r9700
• rocm
• rtx3090
• spark
• speculative-decoding
• speculative-prefill
• strix-halo

Rank #2,698 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 6,051

  Rank 6,051: peonist-ai/halogen-flash-server

  The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

  1,018 starsShellOther licenseLast push Oct 18, 2026

• 4,053

  Rank 4,053: Tencent/AngelSlim

  Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

  1,762 starsPythonOther licenseLast push Oct 14, 2026

• 1,074

  Rank 1,074: Osmantic/ODS

  ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

  7,571 starsPythonApache-2.0Last push Oct 18, 2026

• 7,564

  Rank 7,564: pegainfer-project/pegainfer

  Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

  724 starsRustApache-2.0Last push Oct 17, 2026

• 3,844

  Rank 3,844: dphnAI/sonar

  Large-scale LLM inference engine

  1,877 starsPythonAGPL-3.0Last push Oct 18, 2026

• 5,991

  Rank 5,991: StayLameBro/backburner

  Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

  1,033 starsPythonMITLast push Oct 13, 2026