harleyszhang / llm_note
LLM notes, including model inference, transformer model structure, and lightllm framework code analysis notes
☆30Updated this week
Related projects ⓘ
Alternatives and complementary repositories for llm_note
- TensorRT encapsulation, learn, rewrite, practice.☆24Updated 2 years ago
- ☆56Updated this week
- async inference for machine learning model☆26Updated 2 years ago
- ☆97Updated 7 months ago
- ☆23Updated last year
- 该代码与B站上的视频 https://www.bilibili.com/video/BV18L41197Uz/?spm_id_from=333.788&vd_source=eefa4b6e337f16d87d87c2c357db8ca7 相关联。☆60Updated last year
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆44Updated last year
- Llama3 Streaming Chat Sample☆23Updated 6 months ago
- Large Language Model Onnx Inference Framework☆24Updated 3 weeks ago
- Some common CUDA kernel implementations (Not the fastest).☆13Updated 2 weeks ago
- ☆32Updated last month
- An onnx-based quantitation tool.☆70Updated 10 months ago
- b站上的课程☆70Updated last year
- ☆117Updated last year
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆32Updated 3 months ago
- A large number of cuda/tensorrt cases . 大量案例来学习cuda/tensorrt☆105Updated 2 years ago
- ☆136Updated this week
- learning how CUDA works☆162Updated 2 months ago
- ☆140Updated 6 months ago
- ☆96Updated 3 years ago
- Using pattern matcher in onnx model to match and replace subgraphs.☆75Updated 9 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!☆22Updated 2 months ago
- ☆42Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆52Updated 3 months ago
- Quick and Self-Contained TensorRT Custom Plugin Implementation and Integration☆36Updated 4 months ago
- A Toolkit to Help Optimize Large Onnx Model☆146Updated 5 months ago
- ☆125Updated 9 months ago
- NVIDIA TensorRT Hackathon 2023复赛选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆40Updated last year
- ☆18Updated 10 months ago
- TensorRT 2022复赛方案: 首个基于Transformer的图像重建模型MST++的TensorRT模型推断优化☆135Updated 2 years ago