Hacktoberfest 2026：メンテナが10月に向けて印を付けた、オープンで初心者向けの issue。 Hacktoberfest の issue を見る

RFE: Add support for more floating point low-precision ML data types (`bfloat16`, `fp8`, `nvfp4`)

オープン
  • 何か問題がありますか？
#930 コメント 17 件 リアクション 2 件 担当者 0 名 GitHub で見る

まだ誰も着手していません。

評価

難易度
5/5
見積もり時間
1週間以上
初心者へのやさしさ
15/100
issue の種類
機能追加
明瞭さ
おおむね明確
活発さ
静か
技術スタック
machine-learning
領域
ai

調査の方向性

The payload names no source files. The spec-level entry point is the MLOperandDataType enum and the buffer compatibility tables that the issue says must be extended. Read the existing comment thread first, since 17 comments with no decision suggests unresolved questions about E4M3 versus E5M2 and the 4-bit block-scaled design. Done would mean a settled proposal for the new types and their backend support, not a patch.

索引モデルが issue の本文から書いたものです。

説明

Agenda+ feature request opset

Problem Statement
Currently, the WebNN API supports standard data types like float32, float16, int8, and uint8. However, the machine learning hardware ecosystem has rapidly migrated toward specialized, low-precision floating-point formats to handle the extreme memory bandwidth and compute demands of modern Large Language Models (LLMs) and diffusion models.

Developers bringing state-of-the-art models to the web are currently forced into a strict dilemma:

  1. Upcast to keep precision: Converting native bfloat16 or fp8 models to float32 respective float16 preserves the model's accuracy and dynamic range, but immediately bloats the memory footprint and exacerbates memory bandwidth bottlenecks, which can be fatal for client-side inference.
  2. Quantize to integer to save memory: Converting to int8 or int4 achieves the desired performance and footprint, but sacrifices precision. Integers space values uniformly, which crushes the activation outliers prevalent in LLMs, leading to a degradation in reasoning quality and perplexity.

Without native WebNN support for modern low-precision floating-point formats, the API forces developers to choose between performance and accuracy, losing out on the hardware-accelerated "best of both worlds" that these new formats were designed to provide.

The Case for Each Format

  1. bfloat16 (Brain Floating Point)

    • Context: Widely used as the default format for training modern AI models because its 8-bit exponent matches float32, preventing gradient underflow/overflow.
    • Issue: Porting a natively bfloat16-trained model to WebNN currently requires an offline conversion to float32 (doubling the model size) or float16 (which requires careful scaling to avoid out-of-bounds errors).

  2. fp8 (OCP 8-bit Floating Point - E4M3 & E5M2)

    • Context: Now standardized by the Open Compute Project and natively supported by current-gen hardware (NVIDIA Hopper/Blackwell, Ryzen AI, RDNA4, Intel XE2 (Lunar Lake, ARC B-series)).
    • Issue: fp8 acts as the perfect middle ground between the two extremes mentioned above. It provides the memory footprint of int8 while maintaining the dynamic range of a floating-point exponent, allowing it to handle activation outliers without precision loss.

  3. nvfp4 (4-bit Microscaled Floating Point)

    • Context: Introduced with NVIDIA's Blackwell architecture, this format represents the bleeding edge of sub-byte quantization. It utilizes a two-level microscaling block approach (sharing an FP8 scale across 16 values) to drastically reduce quantization error compared to pure integer 4-bit.
    • Issue: Allowing hardware-accelerated 4-bit floating-point inference in the browser would be a massive leap for client-side LLM execution, cutting memory usage by ~3.5x compared to FP16 while maintaining near-baseline accuracy.

Proposed Solution
Update the MLOperandDataType enum and underlying buffer compatibility tables to include:

  • bfloat16
  • fp8 (potentially differentiating between E4M3 and E5M2 variants)
  • nvfp4 (or a generic hardware-agnostic equivalent for 4-bit block-scaled floating point)

Use Cases & Benefits

  • Quicker Model Porting: Developers can load original weights directly into the graph without complex offline upcasting/re-quantization pipelines.
  • Higher Quantization Accuracy: Floating-point quantization (fp8, nvfp4) retains the dynamic range of activations much better than standard integer quantization, reducing perplexity degradation.
  • Reduced Memory Pressure: Keeping tensors in their ultra-low precision formats slashes both memory footprint and memory bandwidth bottlenecks during inference on edge devices.
主要言語
Bikeshed
スター
566
フォーク
72
平均マージ
6日 5時間
マージ済み PR（30日）
1

環境構築

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

webmachinelearning/webnn のほかの issue

webmachinelearning/webnn の issue をすべて見る

似ている issue

AI Infra & Agents の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。