kvcache-ai/ktransformers — 18,478 Stars
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Watch Episode
About This Repo#
kvcache-ai/ktransformers — 18,478 ⭐
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations - kvcache-ai/ktransformers
Narration#
Your LLM is stuck on one GPU. KTransformers mixes them all. Eighteen thousand stars. A flexible framework that runs inference across heterogeneous hardware — GPUs, CPUs, NPUs — whatever you have. It optimizes and distributes the workload so you get maximum throughput from mixed hardware. One framework, any silicon. Link in bio. New repos every day.
Watch#
AprilNEA/OpenLogi — 12,246 Stars
⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No account, no telemetry.
IlhamriSKY/TEDI — 147 Stars
Terminal Director. One lightweight app, eight features, your whole dev workflow in a single window.
kunchenguid/gnhf — 3,848 Stars
good night, have fun