"Adaptive Hybrid Quantization Framework for deploying 7B+ LLMs on low-VRAM devices (e.g., GTX 1050). Features surgical block alignment and Numba-accelerated inference.
☆25Jan 14, 2026Updated 6 months ago
Alternatives and similar repositories for QKV-Core
Users that are interested in QKV-Core are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Trion Core☆15Jan 2, 2026Updated 6 months ago
- NoteCraft is a full-stack web app built with Django, Celery, and Next.js that lets users upload academic PDFs, generate AI-powered notes,…☆41Updated this week
- Framework to deal with Portuguese Tax Authority Audit Files and e-factura web services☆20Jun 17, 2026Updated last month
- LLamaHTML is a simple html file to communicate with a running llamacpp llama-server☆24Aug 5, 2025Updated 11 months ago
- A streamlined, modular Z-Image Turbo workflow supporting T2I & I2I, with advanced upscale and restoration options for ComfyUI.☆20Dec 7, 2025Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A pseudo-Fable mode for Claude Opus — Fable-style planning, verification, and multi-agent discipline as a Claude Code skill set. Unoffici…☆20Jul 8, 2026Updated last week
- Spec-driven iterative development companion CLI for OpenCode.☆17Jun 7, 2026Updated last month
- An app which uses inpainting to create an infinitely scrolling image☆11Jun 11, 2024Updated 2 years ago
- Octahedral Impostors implementation for Godot Game Engine☆13Oct 29, 2023Updated 2 years ago
- Adaptive Modular Network (AMN) a potentially novel machine learning architecture capable of producing models which can learn at inference…☆57Mar 10, 2025Updated last year
- Connect Chromium to LLM agents via token-efficient DOM compression. 50-200 tokens per page.☆20Updated this week
- ☆34May 21, 2026Updated 2 months ago
- A tool to generate river meshes with flow and foam maps based on bezier curves.☆11Aug 18, 2022Updated 3 years ago
- Physics systems for flecs☆13Jun 29, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- win32 native frontend for llama-cli☆14Nov 2, 2024Updated last year
- optimal-equipment search engine (Google OR-Tools CP-SAT solver) that, given a Wakfu character's desired stats, finds the best combination…