openvinotoolkit / mlasLinks
☆11Updated 4 months ago
Alternatives and similar repositories for mlas
Users that are interested in mlas are comparing it to the libraries listed below
Sorting:
- ONNX Script editor & visualiser running completely in the browser thanks to Pyodide and Netron☆20Updated 2 years ago
- This repository is a read-only mirror of https://gitlab.arm.com/kleidi/kleidiai☆43Updated last week
- Inference TinyLlama models on ncnn☆24Updated last year
- An easy way to run, test, benchmark and tune OpenCL kernel files☆23Updated last year
- Using OpenVINO to speed up MeloTTS inference☆11Updated 7 months ago
- Snapdragon Neural Processing Engine (SNPE) SDKThe Snapdragon Neural Processing Engine (SNPE) is a Qualcomm Snapdragon software accelerate…☆35Updated 3 years ago
- ☆123Updated last year
- This is a balanced dataset for English homograph disambiguation (HD), generated with Meta's Llama 2-Chat 70B model.☆18Updated last year
- ☆32Updated 10 months ago
- AI Edge Quantizer: flexible post training quantization for LiteRT models.☆41Updated last week
- ☆40Updated 2 years ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆33Updated 2 years ago
- Experiments with BitNet inference on CPU☆55Updated last year
- Loop Nest - Linear algebra compiler and code generator.☆22Updated 2 years ago
- Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK☆68Updated last week
- ncnn HiFi-GAN☆26Updated 8 months ago
- UIE(Universal Information Extraction) infer by ncnn☆12Updated 8 months ago
- JAX bindings for the flash-attention3 kernels☆11Updated 10 months ago
- Estimating hardware and cloud costs of LLMs and transformer projects☆16Updated last year
- ggml学习笔记,ggml是一个机器学习的推理框架☆15Updated last year
- Course Project for COMP4471 on RWKV☆17Updated last year
- [WIP] Better (FP8) attention for Hopper☆30Updated 3 months ago
- Explore training for quantized models☆18Updated this week
- Test data for DALI project☆43Updated last week
- Inference RWKV with multiple supported backends.☆48Updated this week
- C++ implementations for various tokenizers (sentencepiece, tiktoken etc).☆23Updated last week
- A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB,…☆17Updated last year
- C99/C++ header-only library for division via fixed-point multiplication by inverse☆52Updated last year
- 3rd party dependencies for DALI project☆10Updated this week
- ☆11Updated 4 years ago