benja263 / Integer-Only-Inference-for-Deep-Learning-in-Native-CLinks
Converting a deep neural network to integer-only inference in native C via uniform quantization and the fixed-point representation.
☆25Updated 3 years ago
Alternatives and similar repositories for Integer-Only-Inference-for-Deep-Learning-in-Native-C
Users that are interested in Integer-Only-Inference-for-Deep-Learning-in-Native-C are comparing it to the libraries listed below
Sorting:
- This is the open-source version of TinyTS. The code is dirty so far. We may clean the code in the future.☆18Updated last year
- QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX☆151Updated last week
- A tool to deploy Deep Neural Networks on PULP-based SoC's☆82Updated 5 months ago
- Fork of upstream onnxruntime focused on supporting risc-v accelerators☆88Updated 2 years ago
- ☆31Updated 2 years ago
- LCAI-TIHU SW is a software stack of the AI inference processor based on RISC-V☆23Updated 2 years ago
- muRISCV-NN is a collection of efficient deep learning kernels for embedded platforms and microcontrollers.☆85Updated last month
- 🧠 Benchmark facility to train networks on different datasets for PyTorch/Brevitas☆26Updated 2 years ago
- Floating-Point Optimized On-Device Learning Library for the PULP Platform.☆36Updated last week
- Low Precision(quantized) Yolov5☆42Updated 4 months ago
- Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv☆85Updated 3 years ago
- A floating-point matrix multiplication implemented in hardware☆31Updated 4 years ago
- ☆38Updated last year
- FRAME: Fast Roofline Analytical Modeling and Estimation☆37Updated last year
- Curated content for DNN approximation, acceleration ... with a focus on hardware accelerator and deployment☆27Updated last year
- HW/SW co-design of sentence-level energy optimizations for latency-aware multi-task NLP inference☆50Updated last year
- Machine-Learning Accelerator System Exploration Tools☆173Updated 2 months ago
- SAMO: Streaming Architecture Mapping Optimisation☆34Updated last year
- ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference☆135Updated 5 months ago
- A Toy-Purpose TPU Simulator☆19Updated last year
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆110Updated 8 months ago
- 关于深度学习算法、框架、编译器、加速器的一些理解☆16Updated 3 years ago
- CSV spreadsheets and other material for AI accelerator survey papers☆176Updated last year
- ☆98Updated last year
- Torch2Chip (MLSys, 2024)☆53Updated 4 months ago
- CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices☆45Updated 5 years ago
- Linux docker for the DNN accelerator exploration infrastructure composed of Accelergy and Timeloop☆56Updated 3 months ago
- The Riallto Open Source Project from AMD☆82Updated 3 months ago
- ☆29Updated 4 years ago
- The official, proof-of-concept C++ implementation of PocketNN.☆34Updated last year