google-coral/coralnpu
google-coral/coralnpu has 2,691 GitHub stars and 375 forks. GitHot measured +4 stars in 24 hours and +18 in 7 days. Last checked 2026-11-13 12:49 UTC. Last push 2026-11-02.
A machine learning accelerator core designed for energy-efficient AI at the edge.
What you can do
- RV32IMF_Zve32x RISC-V instruction set (specifically rv32imf_zve32x_zicsr_zifencei_zbb)
- 32-bit address space for applications and operating system kernels
- Four-stage processor, in-order dispatch, out-of-order retire
- Four-way scalar, two-way vector dispatch
Measured star growth
- in 24h
- +4
- in 7 days
- +18
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
README.md
OriginalCoral NPU
Coral NPU is a hardware accelerator for ML inferencing. Coral NPU is an Open Source IP designed by Google Research and is freely available for integration into ultra-low-power System-on-Chips (SoCs) targeting wearable devices such as hearables, augmented reality (AR) glasses and smart watches.
Coral NPU is a neural processing unit (NPU), also known as an AI accelerator or deep-learning processor. Coral NPU is based on the 32-bit RISC-V Instruction Set Architecture (ISA).
Coral NPU includes three distinct processor components that work together: matrix, vector (SIMD), and scalar.
Coral NPU Architecture Datasheet
Coral NPU Features
Coral NPU offers the following top-level feature set:
- RV32IMF_Zve32x RISC-V instruction set (specifically
rv32imf_zve32x_zicsr_zifencei_zbb) - 32-bit address space for applications and operating system kernels
- Four-stage processor, in-order dispatch, out-of-order retire
- Four-way scalar, two-way vector dispatch
- 128-bit SIMD, 256-bit (future) pipeline
- 8 KB ITCM memory (tightly-coupled memory for instructions)
- 32 KB DTCM memory (tightly-coupled memory for data)
- Both memories are single-cycle-latency SRAM, more efficient than cache memory
- AXI4 bus interfaces, functioning as both manager and subordinate, to interact with external memory and allow external CPUs to configure Coral NPU
System Requirements
- Bazel 8.6.0
- Python 3.9-3.13
See coralnpu.dockerfile for a detailed list of requirements. Our CI systems run most builds and tests using this image.
Verification & Testing
For details on our testing methodologies and how to run or write tests, see the corresponding test READMEs:
Quick Start
# Ensure that test suite passes
bazel run //tests/cocotb:core_mini_axi_sim_cocotb
# Build a binary
bazel build //examples:coralnpu_v2_hello_world_add_floats
# Build the Simulator (non-RVV for shorter build time):
bazel build //tests/verilator_sim:core_mini_axi_sim
# Run the binary on the simulator:
bazel-bin/tests/verilator_sim/core_mini_axi_sim --binary bazel-out/k8-fastbuild-ST-dd8dc713f32d/bin/examples/coralnpu_v2_hello_world_add_floats.elf

Explore related projects
tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
201,584 starshuggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
168,943 starsAUTOMATIC1111/stable-diffusion-webui
Stable Diffusion web UI
165,303 starsComfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
146,622 stars