Tool profile

EfficientMoE/MoE-Infinity

stable

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

huggingfaceinference-enginelarge-language-modelsllm-inferencemixture-of-expertspytorch

Velocity score

0.26/ 10

[STARS]

344

[FORKS]

[CONTRIBUTORS]

[LAST_COMMIT]

3d ago

Score breakdown

601/ 1000

inference · EfficientMoE/MoE-Infinity

Velocity50%

Adoption30%

Maintenance15%

Community5%

[CODE_GROWTH]

672

[INSTALL_VEL]

498

[ACTIVITY]

570

[COMMUNITY_SIGNAL]

610

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).