feat(ir): Change dtype FP8 to FP8e4m3fn and FP8e5m2

[tsung-li]

FP8 has several standards, single DataType could not present all fp8 format, replace FP8 with two formats most frequently used

[gemini-code-assist]

Summary of Changes

Hello @tsung-li, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refines the representation of 8-bit floating-point data types within the system. Instead of a single generic 'FP8' type, it introduces two distinct IEEE 754 standard formats, 'FP8e4m3fn' and 'FP8e5m2', to accurately reflect the various FP8 standards used in practice. This enhancement improves precision and clarity in data type definitions and their usage across the codebase, with corresponding updates to C++ core, Python interfaces, and unit tests.

Highlights

• Granular FP8 Representation: Replaced a single generic 'FP8' data type with two specific IEEE 754 standard formats: 'FP8e4m3fn' and 'FP8e5m2', to accurately reflect different FP8 standards.
• C++ Core Updates: Modified 'include/pypto/core/dtype.h' to introduce new constant codes, static DataType instances, and update bit and string representation logic for the new FP8 types, including adjusting the reserved range for future IEEE float types.
• Python API Alignment: Updated Python bindings ('python/bindings/modules/core.cpp'), convenience constants ('python/pypto/init.py', 'python/pypto/ir/init.py', 'python/pypto/language/init.py'), and type resolution ('python/pypto/language/parser/type_resolver.py') to expose and recognize the new FP8 formats.
• Type Hinting and Printing: Adjusted 'python/pypto/pypto_core/init.pyi' for accurate type hinting and 'src/ir/transforms/python_printer.cpp' for correct string conversion of the new FP8 types.
• Comprehensive Test Updates: Modified 'tests/ut/core/test_dtype.py' to ensure all existing tests for FP8 functionality (existence, uniqueness, bit size, string representation, float/int predicates) correctly validate the new 'FP8e4m3fn' and 'FP8e5m2' types.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly replaces the generic FP8 data type with the more specific FP8e4m3fn and FP8e5m2 types, which is a great improvement for clarity and standard compliance. The changes are consistently applied across the C++ core, Python bindings, type stubs, and tests. I've found one minor issue regarding an un-updated __all__ export list in one of the Python modules. Otherwise, the implementation is solid.

[tsung-li]

python/pypto/language/init.py

issue fixed, please check the latest code