Comments (3)
Adlik model optimization, focusing on and running on specific hardware to achieve the purpose of acceleration. Because sparsity pruning depends on special algorithms and hardware to achieve acceleration, the usage scenarios are limited. Adlik pruning focuses on channel pruning and filter pruning, which can really reduce the number of parameters and flops. In terms of quantization, Adlik focuses on 8bit quantization because it is easier to accelerate on specific hardware. After testing, it is found that running a small batch of data sets can obtain a quantitative model with little loss of accuracy, so Adlik focuses on this method.
from adlik.
@elsa623 Do you have any other question on model optimizer?
from adlik.
Please open a new issue if you have further questions.
from adlik.
Related Issues (20)
- openvino runtime doesnโt support multiple inputs model
- source_model_type_bug
- Adlik serving support to run original runtime model without Adlik compiler.
- Upgrade OpenVINO To 20221.1.0
- compiler model mnist ckpt-openvino error
- Support Oneflow model as input model in Adlik HOT 1
- start up adlik-serving error HOT 1
- Use case for deep recommendation model HOT 1
- tensorrt runtime load error
- Runtime has upgraded OpenVINO to version 2022.1.0, but compiler has not upgraded
- Release v0.5.0 docker images
- Upgrade tensorflow to the latest version
- Upgrade TensorRT to 8.x version HOT 1
- Upgrade the base ubuntu image to LTS 20.04? HOT 1
- Upgrade PYTHON version from 3.6 to 3.8 HOT 1
- Support Enflame device
- Update CI Image To Ubuntu 20.04 HOT 1
- Support convert Pytorch or TF model to Enflame model directly through Adlik compiler HOT 1
- Adlik Serving should support GPT model, make it convenient to use.
- Adlik support FastTransformer for deploying GPT model
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from adlik.