Relationship with NNCF? about neural-compressor HOT 2 CLOSED

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.