Skip to content
View w23's full-sized avatar

Block or report w23

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.

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
Showing results

experimental linux kernel modules and userspace drivers for RDMA-over-usb4/thunderbolt on consumer hardware

C 50 5 Updated Aug 17, 2026

DeepSeek-V4-Flash across two Strix Halo boxes over 100GbE RDMA: llama.cpp patches, launch config, and measured results. 273 t/s prefill / 21.5 t/s decode at 8k.

HTML 3 Updated Aug 5, 2026

ggml speech-to-text inference for 16+ model families

C++ 1,797 83 Updated Aug 17, 2026

A modern self-hosted music player.

TypeScript 9,523 494 Updated Aug 17, 2026

Режим идиоматического русского мата для AI-агентов. Короче, душевнее, эффективнее. 18+

TypeScript 998 24 Updated Aug 14, 2026

A tool to unlobotomize your NVIDIA card!

Shell 354 173 Updated Aug 13, 2026

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Rust 76,375 4,797 Updated Aug 17, 2026

cut Claude Code token usage by rendering text context as images

TypeScript 7,125 623 Updated Aug 17, 2026

Port of Nvidia LocateAnything-3B on ggml

C++ 451 60 Updated Jul 22, 2026

A QR code generator in a TrueType font: https://qr.jim.sh/

Python 516 14 Updated Jun 28, 2026

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

C 21,490 1,974 Updated Aug 9, 2026

A FUSE-based virtual file system driver for dynamic OpenCode model discovery and configuration mapping.

Python 5 Updated Jun 27, 2026

Reference monospace terminal renderer

C 1,824 70 Updated Jan 10, 2025

Interactive BC-250 CU/WGP live manager using UMR, with TUI controls, safety checks, and boot-table persistence.

Shell 177 9 Updated Jul 30, 2026

Re-enable all 40 CUs on the AMD BC-250 (gfx1013 / Cyan Skillfish). Kernel patch + build script. 1.61x compute scaling verified.

Shell 338 35 Updated Jun 24, 2026

Super Productivity is an advanced todo list app with integrated Timeboxing and time tracking capabilities. It also comes with integrations for Jira, GitLab, GitHub and Open Project.

TypeScript 21,398 1,958 Updated Aug 17, 2026

Python tool for converting files and office documents to Markdown.

Python 174,232 12,733 Updated Jul 29, 2026

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…

Python 2,002 122 Updated Aug 17, 2026
C 4,982 788 Updated May 10, 2026

Log file navigator

C++ 10,557 395 Updated Aug 5, 2026

A harness optimized to smaller LLMs

TypeScript 2,433 163 Updated Aug 15, 2026

Build your own 'AirTags' 🏷 today! Framework for tracking personal Bluetooth devices via Apple's massive Find My network.

Swift 13,390 673 Updated Aug 17, 2026

The best-benchmarked open-source AI memory system. And it's free.

Python 58,423 7,497 Updated Aug 16, 2026

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Go 98,702 5,713 Updated Aug 16, 2026

Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI

Go 2,632 199 Updated Aug 14, 2026

neovim frontend for opencode - a terminal-based AI coding agent

Lua 924 70 Updated Jul 27, 2026

Local AI box on Raspberry Pi.

Python 103 11 Updated May 18, 2026

SpinalHDL implementation of the 3dfx Voodoo Graphics GPU

C 300 15 Updated May 10, 2026
Next