#mixture-of-experts (6 Repositories)
Ranked open-source repositories tagged with #mixture-of-experts, scored by pull request acceptance likelihood and maintainer engagement velocity.
41.2%
27.7h
6 repositories tagged #mixture-of-experts
leonickson1/Swiftlet
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.
NVIDIA/cudnn-frontend
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
giannisanni/pulsar
SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.
brontoguana/krasis
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
EfficientMoE/MoE-Infinity
PyTorch library for cost-effective, fast and easy serving of MoE models.
lucidrains/soft-moe-pytorch
Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch