parallel-computing - GitHub 开源项目专题

1

OpenNMT/CTranslate2

Fast inference engine for Transformer models

C++ ⭐ 4.6k ⑂ 519 MIT · 6 天前推送

cpp cuda

6 天前

最近推送

2

candle-org/step_into_llm

MindSpore online courses: Step into LLM

Jupyter Notebook ⭐ 480 ⑂ 127 Apache-2.0 · 2025-12-22推送

bert chatglm

2025-12-22

最近推送

3

chengzeyi/ParaAttention

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

Python ⭐ 430 ⑂ 45 NOASSERTION · 2025-07-05推送

attention diffusers

2025-07-05