PFCCLab / StarterLinks
【HACKATHON 预备营】飞桨启航计划集训营
☆16Updated 2 months ago
Alternatives and similar repositories for Starter
Users that are interested in Starter are comparing it to the libraries listed below
Sorting:
- 飞桨护航计划集训营☆21Updated 3 weeks ago
- Triton Documentation in Chinese Simplified / Triton 中文文档☆80Updated 4 months ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆60Updated 9 months ago
- PaddlePaddle Developer Community☆123Updated this week
- my cs notes☆54Updated 10 months ago
- A light llama-like llm inference framework based on the triton kernel.☆148Updated 3 weeks ago
- 分层解耦的深度学习推理引擎☆75Updated 6 months ago
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆104Updated last month
- Implement custom operators in PyTorch with cuda/c++☆70Updated 2 years ago
- PaddlePaddle Code Convert Toolkit. 『飞桨』深度学习代码转换工具☆109Updated this week
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆211Updated 3 weeks ago
- ☆35Updated 3 months ago
- Course materials for MIT6.5940: TinyML and Efficient Deep Learning Computing☆55Updated 7 months ago
- ☆294Updated 10 months ago
- ☆250Updated last week
- ☆125Updated last week
- some hpc project for learning☆23Updated last year
- PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)☆94Updated this week
- ☆27Updated last week
- A pupil in the computer world.(Felix Fu)☆243Updated last year
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆175Updated this week
- easy cuda code☆82Updated 8 months ago
- 注释的nano_vllm仓库,并且完成了MiniCPM4的适配以及注册新模型的功能☆39Updated 3 weeks ago
- Parallel Prefix Sum (Scan) with CUDA☆24Updated last year
- b站上的课程☆75Updated 2 years ago
- A simple calculation for LLM MFU.☆44Updated 5 months ago
- Tutorials for writing high-performance GPU operators in AI frameworks.☆130Updated 2 years ago
- 校招、秋招、春招、实习好项目,带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。☆416Updated last month
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆112Updated last year
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆56Updated 9 months ago