Back to Topics Directory
Topic Hub

#mixture-of-experts (6 Repositories)

Ranked open-source repositories tagged with #mixture-of-experts, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

41.2%

Avg Review Latency

27.7h

Filter by language

6 repositories tagged #mixture-of-experts

A TierSwift 552

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.

100.0%
Merge Rate
19h
First Review
100%
1st-Timers
2
Maintainers
A TierPython 915

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.

63.6%
Merge Rate
11h
First Review
70%
1st-Timers
26
Maintainers
A TierRust 207

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.

83.3%
Merge Rate
10h
First Review
0%
1st-Timers
3
Maintainers
D TierC++ 512

brontoguana/krasis

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

0.0%
Merge Rate
5d
First Review
0%
1st-Timers
0
Maintainers
D TierPython 352

EfficientMoE/MoE-Infinity

PyTorch library for cost-effective, fast and easy serving of MoE models.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 348

lucidrains/soft-moe-pytorch

Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
Best Mixture-of-experts Open Source Repositories & C-Rank™ | GetMerged