Comments (2)
Thanks for showing your interest. There are multiple differences if you look at the documents:
- Product position. INC: keep inference on all mainstream frameworks (TF, PT, ONNX RT, and MXNet); NNCF: keep inference on OpenVINO
- User-facing API. INC: unified APIs to support quantization (post-training static/dynamic quantization, training-aware quantization); NNCF: different APIs (training-aware quantization in NNCF and post-training quantization in POT)
- Algorithm innovation. INC: block/tile-based structured sparsity; NNCF: some other algorithms
As you may know, some algorithms are well known in the industry, so the features built on top of them may look similar. We are encouraging users to understand how these products can help your project first and figure out the best way to use them.
from neural-compressor.
close at first and if there is more questions, we can reopen this issue
from neural-compressor.
Related Issues (20)
- Quantized Neural compress model not generating expected results in AMD processor HOT 3
- potential bug in calculating scale,zp in sq
- AssertionError: Framework is not detected correctly from model format. HOT 10
- tensorflow is EOL, will there be a pytorch compatible version? HOT 1
- Segmentation fault (core dumped) when compressing the model. HOT 11
- AWQ fails on ONNX model when a MatMul node's input is a model input/initializer HOT 1
- Quantization of MaxVit model HOT 2
- PostTrainingQuantConfig(quant_level='auto', device='npu', backend="onnxrt_dml_ep") produces fp32 ops. HOT 1
- get_number_of_sockets should take locale into account HOT 2
- how to get layer_mappings for distillation? HOT 1
- Unable to save llama2 after SmoothQuant HOT 1
- AWQ quantization is very slow for ONNX LLMs HOT 1
- How to perform int8 quantisation (not uint8) using ONNX? HOT 1
- How to quantify google/vit-base-patch16-224 pytorch_model.bin to int8 type with neural-compressor HOT 3
- Time based TuningCriterion to keep best performing model? HOT 4
- neural_compressor/adaptor/ox_utils/quantizer.py dfs crash during "basic" tuning HOT 1
- how to get smoothed model before do quantization? HOT 22
- Model execution is single threaded? HOT 1
- Using Neural Compressor on cloud resources HOT 11
- PytorchBasicPruner bug? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from neural-compressor.