bert model split into many layers after int8 quantization
Open
Nobody has claimed this yet.
Module:Quantization
triaged
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
I first post the issue in
https://github.com/NVIDIA/TensorRT-Model-Optimizer/issues/159
I quantize a pytorch bert model using TensorRT-Model-Optimizer
before quantization, I export this model to tensorrt and there is only one layer
but after quantization there are many layers, why?
can this be fixed?
(only part of these layers)
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the before-and-after TensorRT exports shown here and the referenced TensorRT-Model-Optimizer issue. Reproduce the BERT int8 quantization comparison, then determine whether the additional layers are expected or indicate an export problem and document the evidence for a fix.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, pytorch
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100