luliyucoordinate / flash-attention-minimal
Flash Attention in ~100 lines of CUDA (forward pass only)
☆10Updated 10 months ago
Alternatives and similar repositories for flash-attention-minimal:
Users that are interested in flash-attention-minimal are comparing it to the libraries listed below
- ☆24Updated last year
- Awesome code, projects, books, etc. related to CUDA☆16Updated last week
- TensorRT-in-Action 是一个 GitHub 代码库,提供了使用 TensorRT 的代码示例,并有对应 Jupyter Notebook。☆15Updated last year
- A light llama-like llm inference framework based on the triton kernel.☆108Updated this week
- Llama3 Streaming Chat Sample☆22Updated last year
- Created a simple neural network using C++17 standard and the Eigen library that supports both forward and backward propagation.☆9Updated 9 months ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆50Updated 5 months ago
- TensorRT encapsulation, learn, rewrite, practice.☆28Updated 2 years ago
- DETR tensor去除推理过程无用辅助头+fp16部署再次加速+解决转tensorrt 输出全为0问题的新方法。☆12Updated last year
- 搜藏的希望的代码片段☆13Updated last year
- This is a repository to practice multi-thread programming in C++☆24Updated last year
- b站上的课程☆74Updated last year
- 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!☆27Updated 8 months ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆46Updated last year
- An onnx-based quantitation tool.☆71Updated last year
- Optimize softmax in triton in many cases☆20Updated 7 months ago
- Quick and Self-Contained TensorRT Custom Plugin Implementation and Integration☆57Updated 10 months ago
- learn TensorRT from scratch🥰☆14Updated 6 months ago
- HunyuanDiT with TensorRT and libtorch☆17Updated 11 months ago
- async inference for machine learning model☆26Updated 2 years ago
- 🐱 ncnn int8 模型量化评估☆13Updated 2 years ago
- ffmpeg+cuvid+tensorrt+multicamera☆12Updated 3 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆17Updated 7 months ago
- For 2022 Nvidia Hackathon☆21Updated 2 years ago
- ☆29Updated 5 months ago
- <Good Luck To You!> 's work for <TRT-Hackathon-2022-final>☆7Updated 2 years ago
- ☆30Updated last year
- Some common CUDA kernel implementations (Not the fastest).☆17Updated last week
- ☆16Updated last year
- Quantize yolov7 using pytorch_quantization.🚀🚀🚀☆10Updated last year