Skip to content
View MadeBy561's full-sized avatar
3 followers · 2 following

Achievements

Achievement: Pull Sharkx2Achievement: Pair Extraordinairex2Achievement: Quickdraw

Achievements

Achievement: Pull Sharkx2Achievement: Pair Extraordinairex2Achievement: Quickdraw

Block or report MadeBy561

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MadeBy561/README.md

Hunter Wolf

Lifelong developer. Open LLM inference tooling with Local Inference Lab, and the occasional Mac app.

Doorplate Local Inference Lab on GitHub Local Inference Lab on Hugging Face Contact

Local Inference Lab

Local Inference Lab

Proud contributor to Local Inference Lab, a non-profit building open tooling for running large language models on NVIDIA Blackwell hardware. I send patches to the lab's vLLM fork and to b12x, mostly small performance changes in the decode path.

What the lab ships:

Doorplate

Doorplate: names under every thumbnail in Mission Control, the menu bar popover, the quick switcher and the landing tag

Your desktops, with names on the door. Doorplate gives every macOS desktop a name, an icon and a color, and shows it where you look:

  • the menu bar, or the notch on a MacBook
  • under every thumbnail inside Mission Control, on macOS 14 through 27
  • a quick switcher, with the apps open on each desktop
  • a tag when you land on a desktop

Native Swift, Apple Silicon and Intel, notarized. One permission, no account, no analytics.

doorplate.app

Popular repositories Loading

  1. reap-bench reap-bench Public

    Run NVIDIA's GLM-5.2 eval axes (GPQA Diamond, SciCode, ...) against any OpenAI-compatible endpoint — measure what a REAP prune/quant costs.

    Python 12 1

  2. vllm vllm Public

    Forked from local-inference-lab/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Python

  3. sm120-sa-mtp-hybird sm120-sa-mtp-hybird Public

    Python

  4. sm120-dspark-cookbook sm120-dspark-cookbook Public

    Python

  5. b12x b12x Public

    Forked from local-inference-lab/b12x

    Python

  6. blackwell-llm-docker blackwell-llm-docker Public

    Forked from local-inference-lab/blackwell-llm-docker

    Docker images for LLM inference (SGLang + vLLM) on NVIDIA Blackwell GPUs (SM120, CUDA 13.2)

    Shell