Dev Radar
Support
LiveUpdated 2026-10-30 21:12 UTC

ktransformers

ktransformers — 📄 Paper

ktransformers is 📄 Paper. It is ranked #2991 on the Dev Radar, in AI dev tools, first seen 9 days ago and shared in 1 post (1.2k views).

Visit github.com

What ktransformers says about itself

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations - kvcache-ai/ktransformers

ktransformers/papers/kt-ft/ktransformers-finetune.pdf at main · kvcache-ai/ktransformers · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation Files Expand file tree main / ktransformers-finetune.pdf Copy path More file actions More file actions Latest commit History History History 4.65 MB main /…

What people said about ktransformers on X

🚀 Excited to share our new paper, KTransformers-FineTune (KT-FT), developed in collaboration with the amazing @llamafactory_ai team! Fine-tune 671B MoE models with just 16GB GPU VRAM + CPU memory. ⚡ 2.5–21.2× faster than offloading baselines 🧠 Up to 128K-token contexts 🔧 CPU-GPU co-computation, beyond offloading…

— @KVCache_AI, 9 days ago · 26 likes · see the post

Alternatives to ktransformers

ktransformers in numbers

FAQ

What is ktransformers?

📄 Paper It was first shared on X 9 days ago and is ranked #2991 on the Dev Radar.

Is ktransformers free?

It is open source.

Who shared ktransformers?

1 account on X, including @KVCache_AI, in 1 post totalling 1.2k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 21:12 UTC. Full method.