4 repos
EfficientMoE/MoE-Infinity
PyTorch library for cost-effective, fast and easy serving of MoE models.
356
129 commits
jd-opensource/xllm
A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI…
1,559
1,371 commits
jitenkr2030/BFMF
India's Open-Source Ecosystem for Building, Training, and Deploying Foundation Models
1
4 commits
cmavro/PackLLM
Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization
15
1 commits