Pinned Loading

1. ServerlessLLM/ServerlessLLM ServerlessLLM/ServerlessLLM Public

   Serverless LLM Serving for Everyone.

   Python 715 77

2. EfficientMoE/MoE-Infinity EfficientMoE/MoE-Infinity Public

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

   Python 367 41

3. netsys-edinburgh/morphling netsys-edinburgh/morphling Public

   C++ 1 1

4. batchgen-project/batchgen batchgen-project/batchgen Public

   High-Throughput Batch Inference

   C++ 16 1

5. EfficientMoE/Omni-Infinity EfficientMoE/Omni-Infinity Public

   Memory-constrained single-server inference for dense omni-modal generative models (MiniMax-H3 class)

   Python 1