目标是在自制虚拟 GPU 上运行 Qwen2-0.5B INT8 推理。核心痛点是从零实现一个类 CUDA 的执行环境——包括 RISC-V SIMT 解释器、PCI 驱动、用户态运行时库和算子库，全部从无到有手写。
☆19May 31, 2026Updated 5 months ago
Alternatives and similar repositories for gpgpu_driver
Users that are interested in gpgpu_driver are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- CUDA Opt Agent is an LLM-driven toolkit for automated CUDA kernel optimization. It generates baselines from text, specs, or existing .cu …☆14Sep 6, 2026Updated 2 months ago
- Description: Experimental nano-vLLM fork for Qwen3.6 support, CUDA Graph, paged KV cache, and inference-engine learning.☆20Oct 15, 2026Updated 3 weeks ago
- HiPU200 open-source version is a DNN accelerator, using RISC-V instruction set and customized vector/matrix extension.☆10Jan 7, 2022Updated 4 years ago
- A minimal, educational implementation of Flash Attention v2 in CUDA☆14Feb 25, 2026Updated 8 months ago
- Dual-core 16-bit RISC processor☆12Jul 21, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 基于RK3588的边缘预警项目（C++）。 采用Yolov7算法，通过读取输入视频源（RTSP、USB摄像头等），经过自创轻量级目标跟踪算法去重检测，将告警信息实时通过HTTP接口推送，同时将视频源进行转发并利用RTMP协议推送。☆17Apr 28, 2024Updated 2 years ago
- 使用RV1126部署YOLOv5模型☆19May 23, 2024Updated 2 years ago
- Design a cache by using Verilog☆13Jan 12, 2017Updated 9 years ago
- 基于V4L2架构驱动外置USB摄像头实现拍照和查看相册的功能☆16Aug 3, 2025Updated last year
- Buildroot 2025.05 手册 - 中文版（AI高质量翻译）☆18Jun 27, 2025Updated last year
- A dual core RISC-V processor (using PULP platform SoC) implemented on a Digilent Arty S7-50 FPGA board.☆16Aug 7, 2022Updated 4 years ago
- 基于Rust的大模型推理框架☆14Oct 21, 2026Updated 2 weeks ago
- This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference sp…☆75Apr 24, 2026Updated 6 months ago
- Pipelined 64-bit RISC-V core☆17Mar 7, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- SGLang 学习手册 — 9 部分中文工程笔记，对照源码逐章讲解☆39Aug 28, 2026Updated 2 months ago
- ROS Utilities for Industrial Calibration☆19Oct 2, 2025Updated last year
- ☆23Mar 3, 2026Updated 8 months ago
- YOLOv5 series model supports the latest TensorRT10.☆16Jul 24, 2024Updated 2 years ago
- Mutil-Operating Syste with RT-Thread☆19Dec 4, 2021Updated 4 years ago
- Logic Reinforcement Learning☆21Oct 20, 2025Updated last year
- Solutions and Guides to various Kaggle Machine Learning Competitions☆17Sep 24, 2017Updated 9 years ago
- 基于 NVIDIA Isaac Lab 的 Unitree Go2 四足机器狗 RL 步态与控制☆29Jun 2, 2026Updated 5 months ago
- Dual-core RISC-V SoC with JTAG, atomics, SDRAM☆26Jan 1, 2022Updated 4 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- 给NEMU移植Linux Kernel!☆23Jun 1, 2025Updated last year
- 笔记整理 Skill：一个用于 Claude Code 的课程资料、PDF、PPT、题库整理成 Markdown/Obsidian 复习笔记的 Claude Skill。☆17Jun 30, 2026Updated 4 months ago
- 基于RK3588S的4K边缘视觉网关：支持V4L2/RTMP/RTSP视频源、RKNN YOLOv8s推理、RGA+MPP硬件加速、RTMP推流、MQTT上报及多路NPU调度。☆41Aug 24, 2026Updated 2 months ago
- 通过onnxruntime实现yolov8在CPU和GPU上面部署☆27Aug 17, 2024Updated 2 years ago
- Nano vLLM☆27Aug 11, 2025Updated last year
- ☆21Jun 28, 2020Updated 6 years ago
- A playbook for systematically maximizing the performance of deep learning models.☆24Jun 15, 2024Updated 2 years ago
- ☆28Mar 23, 2026Updated 7 months ago
- Speed-of-Light SW efficiency by using ultra low-latency primitives for comms collectives☆13Apr 8, 2026Updated 6 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- This project aims to build an Embedded Linux System, in order to analyze the chip from the power-on execution of the first instruction to…☆456Updated this week
- First complete benchmark for Generative Engine Marketing (GEM), an emerging field that focuses on monetizing generative AI by seamlessly …☆20Jul 4, 2026Updated 4 months ago
- ☆12May 8, 2026Updated 5 months ago
- 基于FPGA的二维卷积识别任务☆26Apr 29, 2023Updated 3 years ago
- RocksDB/LevelDB inspired key-value database in Go☆10Nov 3, 2020Updated 6 years ago
- 6DOF机械臂上，自然语言指令控制，MobileNetV3识别定位，视觉伺服PID抓取☆30Mar 15, 2024Updated 2 years ago
- Rust implementation of Google protocol buffers☆12Oct 20, 2025Updated last year