TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs using low precision formats like FP8 and FP4.
GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
53views this month
Decision brief
TransformerEngine optimizes Transformer model performance with FP8/FP4 precision on NVIDIA GPUs like Hopper, Ada, and Blackwell, boosting throughput and reducing memory usage.
Good fit when
- If you need high-throughput training or inference of Transformer models specifically on compatible NVIDIA GPUs (Hopper, Ada, Blackwell).
- For projects requiring low-precision computation techniques without significant loss in accuracy.
Avoid when
- Avoid if your project is not running on NVIDIA's Hopper, Ada, or Blackwell GPUs.
- If memory usage isn't a critical concern and you prefer higher precision over speed optimization.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (1d since push)
- As of Sep 7, 2026
- Provenance
- Not a fork · Organization account
- As of Sep 7, 2026
- Security (OSV)
- No lockfile
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Backing
Company context for Nvidia. Display-only - separate from trust and ranking.
- Company
- NVIDIA Corporation·GitHub org profile·Jul 11, 2026
- Employees
- 11,528·Wikidata (P1128 employees)·Jul 11, 2026
- Commercial model
- Pure OSS·GitHub org profile (public repos)·Jul 11, 2026
Install
pip install TransformerEngineSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
TransformerEngine is a Python-based library by NVIDIA, focused on enhancing the performance of Transformer models through low-precision computation techniques (FP8 and FP4) on compatible GPUs. It supports frameworks such as PyTorch and JAX, aiming for better training and inference throughput with reduced memory footprint.
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Sep 7, 2026
Categories
Graph entities
Tags
README
.. Copyright (c) 2022 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. See LICENSE for license information. License Transformer Engine ================== Latest News =========== [06/2026] [06/2026] [06/2026] [04/2026] [02/2026] [12/2025] trained with NVFP4 on Transform...
For agents
This page has a .md twin and JSON over the API.