DD-DuDa / TensorRT-in-Action
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
Alternatives and similar repositories for TensorRT-in-Action:
Users that are interested in TensorRT-in-Action are comparing it to the libraries listed below
- ☆24Updated last year
- Flash Attention in ~100 lines of CUDA (forward pass only)☆10Updated 10 months ago
- Tutorials of Extending and importing TVM with CMAKE Include dependency.☆13Updated 6 months ago
- ☆30Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆63Updated 8 months ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆50Updated 5 months ago
- ☆20Updated 4 years ago
- A set of examples around MegEngine☆31Updated last year
- ☆58Updated 5 months ago
- ☆39Updated 3 years ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆46Updated last year
- Some common CUDA kernel implementations (Not the fastest).☆17Updated last week
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆109Updated 11 months ago
- ☆26Updated last year
- An onnx-based quantitation tool.☆71Updated last year
- ☆123Updated last year
- base quantization methods including: QAT, PTQ, per_channel, per_tensor, dorefa, lsq, adaround, omse, Histogram, bias_correction.etc☆44Updated 2 years ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆17Updated 7 months ago
- Optimize softmax in triton in many cases☆20Updated 7 months ago
- ☆16Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆36Updated 2 months ago
- 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。☆67Updated last year
- 🐱 ncnn int8 模型量化评估☆13Updated 2 years ago
- This project is about convolution operator optimization on GPU, include GEMM based (Implicit GEMM) convolution.☆29Updated 4 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆36Updated 3 weeks ago
- Awesome code, projects, books, etc. related to CUDA☆16Updated last week
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆86Updated 3 months ago
- CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API☆30Updated last year
- CUDA 6大并行计算模式 代码与笔记☆60Updated 4 years ago
- ☆23Updated 2 years ago