tensorflow / tensorflow/model-optimization
support all number types in BitpackingEncodingStage
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 349
- Avg merge
- 3d 2h
- Merged PRs (30d)
- 1
Description
System information
- TensorFlow version (you are using): 2.2
- Are you willing to contribute it (Yes/No): Yes
Motivation
currently, BitpackingEncodingStage only supports float32 and float64. Is there any reason not to support int8, int32, etc., in the same way float32 is supported?
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
Locate the BitpackingEncodingStage entry point and inspect how float32 and float64 are currently handled. Determine the intended behavior for integer types such as int8 and int32, then identify the relevant tests or add coverage for each supported number type. Done means the stage supports the requested numeric types without breaking existing floating-point behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100