opensource NPU for LLM inference (this run gpt2)
☆233Feb 16, 2026Updated 6 months ago
Alternatives and similar repositories for tiny-NPU
Users that are interested in tiny-NPU are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- FSA: Fusing FlashAttention within a Single Systolic Array☆192Apr 15, 2026Updated 4 months ago
- The official NaplesPU hardware code repository☆36Jul 27, 2019Updated 7 years ago
- Open-source Neural Processing Unit (NPU) from China ❤☆53Jan 29, 2025Updated last year
- SAURIA (Systolic-Array tensor Unit for aRtificial Intelligence Acceleration) is an open-source Convolutional Neural Network accelerator b…☆112Nov 26, 2025Updated 8 months ago
- A machine learning accelerator core designed for energy-efficient AI at the edge.☆2,512Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Open-source 8×8 INT8 systolic array inference accelerator — from RTL to bitstream☆19Aug 2, 2026Updated 2 weeks ago
- Digital HDL Design Full-stack Agents☆183Jul 28, 2026Updated 3 weeks ago
- RISC-V SIMD Superscalar Dual-Issue Processor☆31Apr 24, 2025Updated last year
- This is my hobby project with System Verilog to accelerate LeViT Network which contain CNN and Attention layer.☆39Aug 13, 2024Updated 2 years ago
- This is a brand new implement of GPGPU called Koala GPU which will be compatible with NV GPU micro architecture starting from fermi. It s…☆18May 31, 2026Updated 2 months ago
- SystemVerilog Implementations of CUDA/TensorCore/TPU GEMM Operations☆21Apr 12, 2026Updated 4 months ago
- CoralNPU behavior simulator based on MPACT-Sim☆25Jun 10, 2026Updated 2 months ago
- Chisel implementation of Neural Processing Unit for System on the Chip☆34Aug 5, 2026Updated 2 weeks ago
- IC implementation of Systolic Array for TPU☆369Oct 21, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A minimal tensor processing unit (TPU), inspired by Google's TPU V2 and V1☆1,364Apr 3, 2026Updated 4 months ago
- ☆44Updated this week
- Berkeley's Spatial Array Generator☆1,432Jun 30, 2026Updated last month
- Alpha64 R10000 Two-Way Superscalar Processor☆12May 6, 2019Updated 7 years ago
- ☆244Jun 25, 2025Updated last year
- Contract-Aware RTL Code Generation Agents with Temporal Tracing, Slicing and Formal Verification☆24Jan 28, 2026Updated 6 months ago
- 1G‑style Ethernet PHY PCS block in Sky130 using OpenLane☆18Feb 15, 2026Updated 6 months ago
- verilog module add prefix script 可用于ysyx项目添加学号☆13Mar 4, 2024Updated 2 years ago
- A heterogeneous accelerator-centric compute cluster☆52Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A verilog hardware description model of LLM for FPGA / SoC - runs newest LLM models☆27Jan 24, 2026Updated 6 months ago
- [TECS'23] A project on the co-design of Accelerators and CNNs.☆22Dec 10, 2022Updated 3 years ago
- OBI SystemVerilog synthesizable interconnect IPs for on-chip communication☆23Aug 6, 2026Updated last week
- "aura" my super-scalar O3 cpu core☆26May 25, 2024Updated 2 years ago
- A Heterogeneous GPU Platform for AI and Neural Graphics☆67Updated this week
- A hardware accelerator for General Matrix Multiply, developed in SystemC using ESP.☆20May 26, 2021Updated 5 years ago
- Network on-Chip (NoC) simulator for simulating intra-chip data flow in Neural Network Accelerator☆39Dec 22, 2023Updated 2 years ago
- verilog实现TPU中的脉动阵列计算卷积的module☆175May 10, 2025Updated last year
- This project aims to develop a novel neuromorphic NoC architecture based on RISC-V ISA to support spiking neural network applications, an…☆23Nov 27, 2025Updated 8 months 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.
- RV64GC Linux Capable RISC-V Core☆68Aug 7, 2026Updated last week
- RISC-V vector and tensor compute extensions for Vortex GPGPU acceleration for ML workloads. Optimized for transformer models, CNNs, and g…☆25Apr 25, 2025Updated last year
- NPUsim: Full-Model, Cycle-Level, and Value-Aware Simulator for DNN Accelerators☆56Updated this week
- DUTH RISC-V Superscalar Microprocessor☆35Oct 23, 2024Updated last year
- The wafer-native AI accelerator simulation platform and inference engine.☆63Jan 1, 2026Updated 7 months ago
- ☆35Jul 9, 2025Updated last year
- Deploy llama2.c on the OpenLA500 SoC with custom AI accelerator (FPGA)☆23Jun 16, 2026Updated 2 months ago