Pinned Loading

1. FlashMLA FlashMLA Public

   Forked from vllm-project/FlashMLA

   C++

2. InferLLM InferLLM Public

   Forked from MegEngine/InferLLM

   a lightweight LLM model inference framework

   C++

3. mperf mperf Public

   Forked from MegEngine/mperf

   mperf是一个面向移动/嵌入式平台的算子性能调优工具箱

   C++

4. vllm-project/vllm vllm-project/vllm Public

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 67.9k 12.7k

5. NVIDIA/nccl NVIDIA/nccl Public

   Optimized primitives for collective multi-GPU communication

   C++ 4.4k 1.1k

6. vllm-project/FlashMLA vllm-project/FlashMLA Public

   Forked from deepseek-ai/FlashMLA

   C++ 10 17