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

376 stars 48 forks 376 watchers Python Apache License 2.0
huggingface inference-engine large-language-models llm-inference mixture-of-experts pytorch
1 Open Issue Need Help Last updated: Nov 1, 2026

Open Issues Need Help

View All on GitHub

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

Python
#huggingface#inference-engine#large-language-models#llm-inference#mixture-of-experts#pytorch