A light llama-like llm inference framework based on the triton kernel.
☆172Jan 5, 2026Updated 2 months ago
Alternatives and similar repositories for lite_llama
Users that are interested in lite_llama are comparing it to the libraries listed below
Sorting:
- ☆40Updated this week
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆115Jul 11, 2025Updated 7 months 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。☆507Oct 28, 2025Updated 4 months ago
- LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.☆867Dec 10, 2025Updated 2 months ago
- 一些采用opencv3图像处理库做的一些项目，有检测人脸位置、人脸特效、头顶加LOGO等☆11Oct 31, 2022Updated 3 years ago
- 校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library st…☆3,345Jun 22, 2025Updated 8 months ago
- 一个轻量化的大模型推理框架☆21May 26, 2025Updated 9 months ago
- 本仓库在OpenVINO推理框架下部署Nanodet检测算法，并重写预处理和后处理部分，具有超高性能！让你在Intel CPU平台上的检测速度起飞！ 并基于NNCF和PPQ工具将模型量化(PTQ)至int8精度，推理速度更快！☆16Jun 14, 2023Updated 2 years ago
- ☆123Updated this week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆909Updated this week
- 一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework☆1,751Feb 23, 2026Updated 2 weeks ago
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆9,815Feb 25, 2026Updated last week
- A CUDA tutorial to make people learn CUDA program from 0☆269Jul 9, 2024Updated last year
- how to learn PyTorch and OneFlow☆487Mar 22, 2024Updated last year
- ☆15Jun 22, 2025Updated 8 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆79Aug 12, 2024Updated last year
- A simple neural network inference framework☆25Aug 1, 2023Updated 2 years ago
- how to optimize some algorithm in cuda.☆2,841Feb 28, 2026Updated last week
- flash attention tutorial written in python, triton, cuda, cutlass☆490Jan 20, 2026Updated last month
- 68th palce solution in Kaggle Humpback Whale Identification.☆11Jul 6, 2023Updated 2 years ago
- Quantize yolov5 using pytorch_quantization.🚀🚀🚀☆14Oct 24, 2023Updated 2 years ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆73Sep 8, 2024Updated last year
- 使用 CUDA C++ 实现的 llama 模型推理框架☆64Nov 8, 2024Updated last year
- 深度学习系统笔记，包含深度学习数学基础知识、神经网络基础部件详解、深度学习炼丹策略、模型压缩算法详解。☆513Dec 11, 2025Updated 2 months ago
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆255Feb 13, 2026Updated 3 weeks ago
- ☆315Oct 9, 2024Updated last year
- ☆47Mar 27, 2023Updated 2 years ago
- ☆27May 27, 2024Updated last year
- Implementation and optimization of matrix multiplication on single CPU (HPC-THU-2023-Autumn)☆18Feb 27, 2024Updated 2 years ago
- An onnx-based quantitation tool.☆70Jan 8, 2024Updated 2 years 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☆168Aug 11, 2025Updated 6 months ago
- 【A common used C++ & Python DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流☆2,250Mar 1, 2026Updated last week
- Build a Claude Code–like CLI coding agent from scratch.☆105Jan 22, 2026Updated last month
- From Minimal GEMM to Everything☆183Feb 10, 2026Updated 3 weeks ago
- WPF+litegraph.js+Webview实现的混合图节点编辑器☆25May 2, 2025Updated 10 months ago
- Deep insight tensorrt, including but not limited to qat, ptq, plugin, triton_inference, cuda☆23Mar 1, 2026Updated last week
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆194Jan 28, 2025Updated last year
- ☆79May 16, 2023Updated 2 years ago
- my cs notes☆60Oct 14, 2024Updated last year