# riscv-llm

**Repository Path**: openkylin/riscv-llm

## Basic Information

- **Project Name**: riscv-llm
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2024-05-08
- **Last Updated**: 2025-12-31

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# `Running LLM in RISC-V`

## Directory Structure

```shell
.
├── dist            # 构建pytorch wheel
├── docs            # 文档
├── gemma.app       # cli chat app with Gemma
├── patches         # Patches for the pytorch, inferllm
├── model           # 模型参数文件，gemma模型由于超出大文件存储容量未上传
├── tinyllm         # cli story teller app with tinyLLM
└── web.app         # web app with Gemma and tinyLLM
```

## Introduction

各个应用使用说明分别见各自的 `README.md` 文件。

## TODO

- [ ] performance optimization patches for pytorch
- [ ] web.app user interface optimization
- [ ] training and fine-tuning a smaller version of LLM for RISC-V

## References and Acknowledgements
感谢以下开源软件和相关的作者：
Google，pytorch团队，MegEngine团队，openKylin团队，以及开源作者tiangolo，hmsgit等。
- https://gitee.com/openkylin
- https://www.kaggle.com/models/google/gemma/frameworks/pyTorch/
- https://github.com/google/gemma.cpp
- https://github.com/pytorch/pytorch
- https://github.com/openkylin
- https://github.com/cindysridykhan/instruct_storyteller_tinyllama2
- https://github.com/MegEngine/InferLLM/
- https://github.com/tiangolo/fastapi
- https://github.com/hmsgit/fastapi-streaming-response
- https://www.openmp.org/