Giter Club home page Giter Club logo

rwkv-tensorrt's Introduction

rwkv-onnx

A converter and basic tester for rwkv onnx

supports

  • fp16
  • fp32
  • onnx opsversions 15/17
  • file sizes > 2GB

Note: fp16+ops15 may not work with cuda erp, but may work with tensorRT

Note: converter requires protobuf 3.20.0

Install with pip install protobuf==3.20.0

rwkv-tensorrt's People

Contributors

dan-wanna-m avatar daquexian avatar

Stargazers

avatar avatar Vincent avatar Phan Hoang avatar avatar

Watchers

avatar

Forkers

daquexian

rwkv-tensorrt's Issues

The world model is damaged after exporting to onnx

with fp16 and version 17.

After exporting the model, attempting to use onnx infering resulted in an error.

onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Load model from RWKV_32_4096_16_17_seq.onnx failed:Type Error: Type parameter (T) of Optype (Mul) bound to different types (tensor(float) and tensor(float16) in node ().

There seems to be a defect in fp16 quantification. Please fix it as soon as possible. Thank you

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.