Cluster 645580

4 repos

Python · 4

llm ·2,604

mixture-of-experts ·2,604

google-colab ·2,336

language-model ·2,336

colab-notebook ·2,336

deep-learning ·2,336

offloading ·2,336

pytorch ·2,336

quantization ·2,336

local-inference ·268

Related clusters

efeslab/fiddler

[ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration

Python

268

39 commits

MobiSense/SpecOffload-public

No description

Python

4 commits

dvmazur/mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

Python

2,336

86 commits

PKU-SEC-Lab/HybriMoE

[DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for…

Python

121

6 commits