Popular repositories Loading

1. LATuner LATuner Public

   An LLM-enhanced Database Tuning System based on Adaptive Surrogate Model

   Python 4 3

2. mtune_repo mtune_repo Public

3. Tuning Tuning Public

   Jupyter Notebook

4. taskflow taskflow Public

   Forked from taskflow/taskflow

   A General-purpose Task-parallel Programming System using Modern C++

   C++

5. tiny-llm tiny-llm Public

   Forked from skyzh/tiny-llm

   A course of LLM inference serving on Apple Silicon for systems engineers.

   Python

6. fastllm fastllm Public

   Forked from ztxz16/fastllm

   fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

   C++