dianhsu / transformer-cpp-cpu
用C++实现一个简单的Transformer模型。 Attention Is All You Need。
☆47Updated 4 years ago
Alternatives and similar repositories for transformer-cpp-cpu:
Users that are interested in transformer-cpp-cpu are comparing it to the libraries listed below
- Swin Transformer C++ Implementation☆62Updated 3 years ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆48Updated 4 months ago
- 分层解耦的深度学习推理引擎☆72Updated last month
- 使用 cutlass 实现 flash-attention 精简版，具有教学意义☆38Updated 7 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆14Updated last year
- ☆19Updated 4 years ago
- Some common CUDA kernel implementations (Not the fastest).☆17Updated last week
- CUDA 6大并行计算模式 代码与笔记☆60Updated 4 years ago
- CPU Memory Compiler and Parallel programing☆25Updated 4 months ago
- ☆20Updated this week
- A tutorial for CUDA&PyTorch☆128Updated 2 months ago
- EasyNN是一个面向教学而开发的神经网络推理框架，旨在让大家0基础也能自主完成推理框架编写！☆26Updated 6 months ago
- ☆145Updated 2 months ago
- play gemm with tvm☆89Updated last year
- Free resource for the book AI Compiler Development Guide☆43Updated 2 years ago
- ☆58Updated 4 months ago
- simplify >2GB large onnx model☆54Updated 3 months ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆46Updated last year
- ☆36Updated 5 months ago
- llama 2 Inference☆42Updated last year
- ☆113Updated last year
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆17Updated 5 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆60Updated 7 months ago
- ☆95Updated 3 years ago
- ☆59Updated 2 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆106Updated 6 months ago
- ☆29Updated 11 months ago
- autoTVM神经网络推理代码优化搜索演示，基于tvm编译开源模型centerface，并使用autoTVM搜索最优推理代码， 最终部署编译为c++代码，演示平台是cuda，可以是其他平台，例如树莓派，安卓手机，苹果手机．Thi is a demonstration of …☆27Updated 3 years ago
- A light llama-like llm inference framework based on the triton kernel.☆100Updated 2 weeks ago
- ☆16Updated last year