René's URL Explorer Experiment


Title: GitHub - NVIDIA/TransformerEngine: A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

Open Graph Title: GitHub - NVIDIA/TransformerEngine: A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

X Title: GitHub - NVIDIA/TransformerEngine: A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

Description: A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference. - NVIDIA/TransformerEngine

Open Graph Description: A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance...

X Description: A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance...

Opengraph URL: https://github.com/NVIDIA/TransformerEngine

X: @github

direct link

Domain: patch-diff.githubusercontent.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:0e6d5733-de9e-3544-fc8b-4e9c4b8827fa
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-idAB16:D4A52:325792E:436440E:696F27FD
html-safe-nonce82d69321a650136fb21718366537589c3fe10245379f952fc00aafc744f4f9dc
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJBQjE2OkQ0QTUyOjMyNTc5MkU6NDM2NDQwRTo2OTZGMjdGRCIsInZpc2l0b3JfaWQiOiIzOTIzMDU2MzAzMDAyODQ5MjUiLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmaccbdc12f4710069f32cbf9d89378ed8a3c344151c946ee508fe4b2459388eec43
hovercard-subject-tagrepository:539057023
github-keyboard-shortcutsrepository,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location//
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/NVIDIA/TransformerEngine
twitter:imagehttps://opengraph.githubassets.com/7152e8282726573be3e0e4b633a30ab6a6d2a0b79b3987b75126328d7964540a/NVIDIA/TransformerEngine
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/7152e8282726573be3e0e4b633a30ab6a6d2a0b79b3987b75126328d7964540a/NVIDIA/TransformerEngine
og:image:altA library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance...
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
Noneb278ad162d35332b6de714dfb005de04386c4d92df6475522bef910f491a35ee
turbo-cache-controlno-preview
go-importgithub.com/NVIDIA/TransformerEngine git https://github.com/NVIDIA/TransformerEngine.git
octolytics-dimension-user_id1728152
octolytics-dimension-user_loginNVIDIA
octolytics-dimension-repository_id539057023
octolytics-dimension-repository_nwoNVIDIA/TransformerEngine
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id539057023
octolytics-dimension-repository_network_root_nwoNVIDIA/TransformerEngine
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
release39aed5006635ab6f45e6b77d23e73b08a00272a3
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#start-of-content
https://patch-diff.githubusercontent.com/
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FNVIDIA%2FTransformerEngine
GitHub CopilotWrite better code with AIhttps://github.com/features/copilot
GitHub SparkBuild and deploy intelligent appshttps://github.com/features/spark
GitHub ModelsManage and compare promptshttps://github.com/features/models
MCP RegistryNewIntegrate external toolshttps://github.com/mcp
ActionsAutomate any workflowhttps://github.com/features/actions
CodespacesInstant dev environmentshttps://github.com/features/codespaces
IssuesPlan and track workhttps://github.com/features/issues
Code ReviewManage code changeshttps://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilitieshttps://github.com/security/advanced-security
Code securitySecure your code as you buildhttps://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they starthttps://github.com/security/advanced-security/secret-protection
Why GitHubhttps://github.com/why-github
Documentationhttps://docs.github.com
Bloghttps://github.blog
Changeloghttps://github.blog/changelog
Marketplacehttps://github.com/marketplace
View all featureshttps://github.com/features
Enterpriseshttps://github.com/enterprise
Small and medium teamshttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
App Modernizationhttps://github.com/solutions/use-case/app-modernization
DevSecOpshttps://github.com/solutions/use-case/devsecops
DevOpshttps://github.com/solutions/use-case/devops
CI/CDhttps://github.com/solutions/use-case/ci-cd
View all use caseshttps://github.com/solutions/use-case
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
View all industrieshttps://github.com/solutions/industry
View all solutionshttps://github.com/solutions
AIhttps://github.com/resources/articles?topic=ai
Software Developmenthttps://github.com/resources/articles?topic=software-development
DevOpshttps://github.com/resources/articles?topic=devops
Securityhttps://github.com/resources/articles?topic=security
View all topicshttps://github.com/resources/articles
Customer storieshttps://github.com/customer-stories
Events & webinarshttps://github.com/resources/events
Ebooks & reportshttps://github.com/resources/whitepapers
Business insightshttps://github.com/solutions/executive-insights
GitHub Skillshttps://skills.github.com
Documentationhttps://docs.github.com
Customer supporthttps://support.github.com
Community forumhttps://github.com/orgs/community/discussions
Trust centerhttps://github.com/trust-center
Partnershttps://github.com/partners
GitHub SponsorsFund open source developershttps://github.com/sponsors
Security Labhttps://securitylab.github.com
Maintainer Communityhttps://maintainers.github.com
Acceleratorhttps://github.com/accelerator
Archive Programhttps://archiveprogram.github.com
Topicshttps://github.com/topics
Trendinghttps://github.com/trending
Collectionshttps://github.com/collections
Enterprise platformAI-powered developer platformhttps://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security featureshttps://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/premium-support
Pricinghttps://github.com/pricing
Search syntax tipshttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentationhttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FNVIDIA%2FTransformerEngine
Sign up https://patch-diff.githubusercontent.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=NVIDIA%2FTransformerEngine
Reloadhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Reloadhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Reloadhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
NVIDIA https://patch-diff.githubusercontent.com/NVIDIA
TransformerEnginehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FNVIDIA%2FTransformerEngine
Fork 609 https://patch-diff.githubusercontent.com/login?return_to=%2FNVIDIA%2FTransformerEngine
Star 3.1k https://patch-diff.githubusercontent.com/login?return_to=%2FNVIDIA%2FTransformerEngine
docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.htmlhttps://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html
Apache-2.0 license https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/LICENSE
3.1k stars https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/stargazers
609 forks https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/forks
Branches https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/branches
Tags https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tags
Activity https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/activity
Star https://patch-diff.githubusercontent.com/login?return_to=%2FNVIDIA%2FTransformerEngine
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FNVIDIA%2FTransformerEngine
Code https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Issues 280 https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/issues
Pull requests 107 https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/pulls
Discussions https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/discussions
Actions https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/actions
Security Uh oh! There was an error while loading. Please reload this page. https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/security
Please reload this pagehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Insights https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/pulse
Code https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Issues https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/issues
Pull requests https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/pulls
Discussions https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/discussions
Actions https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/actions
Security https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/security
Insights https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/pulse
Brancheshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/branches
Tagshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tags
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/branches
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tags
1,569 Commitshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/commits/main/
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/commits/main/
.githubhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/.github
.githubhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/.github
3rdpartyhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/3rdparty
3rdpartyhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/3rdparty
benchmarkshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/benchmarks
benchmarkshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/benchmarks
build_toolshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/build_tools
build_toolshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/build_tools
docshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/docs
docshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/docs
exampleshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/examples
exampleshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/examples
qahttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/qa
qahttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/qa
testshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/tests
testshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/tests
transformer_enginehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/transformer_engine
transformer_enginehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/tree/main/transformer_engine
.clang-formathttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/.clang-format
.clang-formathttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/.clang-format
.gitignorehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/.gitignore
.gitignorehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/.gitignore
.gitmoduleshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/.gitmodules
.gitmoduleshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/.gitmodules
.pre-commit-config.yamlhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/.pre-commit-config.yaml
.pre-commit-config.yamlhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/.pre-commit-config.yaml
Acknowledgements.txthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/Acknowledgements.txt
Acknowledgements.txthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/Acknowledgements.txt
CONTRIBUTING.rsthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/CONTRIBUTING.rst
CONTRIBUTING.rsthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/CONTRIBUTING.rst
CPPLINT.cfghttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/CPPLINT.cfg
CPPLINT.cfghttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/CPPLINT.cfg
LICENSEhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/LICENSE
LICENSEhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/LICENSE
MANIFEST.inhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/MANIFEST.in
MANIFEST.inhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/MANIFEST.in
README.rsthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/README.rst
README.rsthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/README.rst
SECURITY.mdhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/SECURITY.md
SECURITY.mdhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/SECURITY.md
pylintrchttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/pylintrc
pylintrchttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/pylintrc
pyproject.tomlhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/pyproject.toml
pyproject.tomlhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/pyproject.toml
setup.pyhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/setup.py
setup.pyhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/setup.py
READMEhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Contributinghttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Apache-2.0 licensehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Securityhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
https://opensource.org/licenses/Apache-2.0
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#transformer-engine
Quickstarthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#examples
Installationhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#installation
User Guidehttps://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html
Exampleshttps://github.com/NVIDIA/TransformerEngine/tree/main/examples
FP8 Convergencehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#fp8-convergence
Integrationshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#integrations
Release noteshttps://docs.nvidia.com/deeplearning/transformer-engine/documentation-archive.html
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#latest-news
NVIDIA Blackwell Architecture Sweeps MLPerf Training v5.1 Benchmarkshttps://developer.nvidia.com/blog/nvidia-blackwell-architecture-sweeps-mlperf-training-v5-1-benchmarks/
Scale Biology Transformer Models with PyTorch and NVIDIA BioNeMo Recipeshttps://developer.nvidia.com/blog/scale-biology-transformer-models-with-pytorch-and-nvidia-bionemo-recipes/
FP8 Training of Large-Scale RL Modelshttps://lmsys.org/blog/2025-11-25-fp8-rl/
Pretraining Large Language Models with NVFP4https://www.arxiv.org/pdf/2509.25149
Native FP8 Mixed Precision Training for Ling 2.0, Open Sourced!https://huggingface.co/blog/im0qianqian/ling-mini-2-fp8-mixed-precision-training-solution
Faster Training Throughput in FP8 Precision with NVIDIA NeMohttps://developer.nvidia.com/blog/faster-training-throughput-in-fp8-precision-with-nvidia-nemo/
How we built DeepL's next-generation LLMs with FP8 for training and inferencehttps://www.deepl.com/en/blog/tech/next-generation-llm-fp8-training
NVFP4 Trains with Precision of 16-bit and Speed and Efficiency of 4-bithttps://developer.nvidia.com/blog/nvfp4-trains-with-precision-of-16-bit-and-speed-and-efficiency-of-4-bit/
Previous Newshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#previous-news
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#what-is-transformer-engine
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#highlights
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#examples
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#pytorch
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#jax
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#flax
Quickstart Notebookhttps://github.com/NVIDIA/TransformerEngine/blob/main/docs/examples/quickstart.ipynb
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#installation
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#system-requirements
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#installation-methods
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#docker-recommended
NVIDIA GPU Cloud (NGC) Cataloghttps://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#pip-installation
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#conda-installation
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#source-installation
See the installation guidehttps://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html#installation-from-source
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#environment-variables
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#compiling-with-flashattention
bughttps://github.com/Dao-AILab/flash-attention/issues/358
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#troubleshooting
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#breaking-changes
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#v17-padding-mask-definition-for-pytorch
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#fp8-convergence
https://github.com/NVIDIA/JAX-Toolbox/tree/main/rosetta/rosetta/projects/t5x#convergence-and-performancehttps://github.com/NVIDIA/JAX-Toolbox/tree/main/rosetta/rosetta/projects/t5x#convergence-and-performance
https://www.mosaicml.com/blog/coreweave-nvidia-h100-part-1https://www.mosaicml.com/blog/coreweave-nvidia-h100-part-1
https://github.com/NVIDIA/JAX-Toolbox/tree/main/rosetta/rosetta/projects/pax#h100-resultshttps://github.com/NVIDIA/JAX-Toolbox/tree/main/rosetta/rosetta/projects/pax#h100-results
https://mp.weixin.qq.com/s/NQT0uKXLbXyh5031zBdeBQhttps://mp.weixin.qq.com/s/NQT0uKXLbXyh5031zBdeBQ
https://www.databricks.com/blog/turbocharged-training-optimizing-databricks-mosaic-ai-stack-fp8https://www.databricks.com/blog/turbocharged-training-optimizing-databricks-mosaic-ai-stack-fp8
https://mp.weixin.qq.com/s/NQT0uKXLbXyh5031zBdeBQhttps://mp.weixin.qq.com/s/NQT0uKXLbXyh5031zBdeBQ
https://github.com/NVIDIA/JAX-Toolbox/tree/main/rosetta/rosetta/projects/pax#h100-resultshttps://github.com/NVIDIA/JAX-Toolbox/tree/main/rosetta/rosetta/projects/pax#h100-results
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#integrations
DeepSpeedhttps://github.com/deepspeedai/DeepSpeed/blob/master/tests/unit/runtime/half_precision/test_fp8.py
Hugging Face Acceleratehttps://huggingface.co/docs/accelerate/main/en/usage_guides/low_precision_training#configuring-transformersengine
Lightninghttps://github.com/Lightning-AI/lightning/issues/17172
MosaicML Composerhttps://github.com/mosaicml/composer/releases/tag/v0.13.1
NVIDIA JAX Toolboxhttps://github.com/NVIDIA/JAX-Toolbox
NVIDIA Megatron-LMhttps://github.com/NVIDIA/Megatron-LM
NVIDIA NeMo Frameworkhttps://github.com/NVIDIA/NeMo-Megatron-Launcher
Amazon SageMaker Model Parallel Libraryhttps://docs.aws.amazon.com/sagemaker/latest/dg/model-parallel-core-features-v2-tensor-parallelism.html
Levanterhttps://github.com/stanford-crfm/levanter
GPT-NeoXhttps://github.com/EleutherAI/gpt-neox
Hugging Face Nanotronhttps://github.com/huggingface/nanotron
Colossal-AIhttps://github.com/hpcaitech/ColossalAI
PeriFlowhttps://github.com/friendliai/periflow-python-sdk
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#contributing
CONTRIBUTING.rsthttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/CONTRIBUTING.rst
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#papers
Attention original paperhttps://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Megatron-LM tensor parallelhttps://arxiv.org/pdf/1909.08053.pdf
Megatron-LM sequence parallelhttps://arxiv.org/pdf/2205.05198.pdf
FP8 Formats for Deep Learninghttps://arxiv.org/abs/2209.05433
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#videos
Stable and Scalable FP8 Deep Learning Training on Blackwell | GTC 2025https://www.nvidia.com/en-us/on-demand/session/gtc24-s62457/
Blackwell Numerics for AI | GTC 2025https://www.nvidia.com/en-us/on-demand/session/gtc25-s72458/
Building LLMs: Accelerating Pretraining of Foundational Models With FP8 Precision | GTC 2025https://www.nvidia.com/gtc/session-catalog/?regcode=no-ncid&ncid=no-ncid&tab.catalogallsessionstab=16566177511100015Kus&search=zoho#/session/1726152813607001vnYK
From FP8 LLM Training to Inference: Language AI at Scale | GTC 2025https://www.nvidia.com/en-us/on-demand/session/gtc25-s72799/
What's New in Transformer Engine and FP8 Training | GTC 2024https://www.nvidia.com/en-us/on-demand/session/gtc24-s62457/
FP8 Training with Transformer Engine | GTC 2023https://www.nvidia.com/en-us/on-demand/session/gtcspring23-s51393
FP8 for Deep Learning | GTC 2023https://www.nvidia.com/en-us/on-demand/session/gtcspring23-s52166/
Inside the Hopper Architecture | GTC 2022https://www.nvidia.com/en-us/on-demand/session/gtcspring22-s42663/
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#previous-news
Floating Point 8: An Introduction to Efficient, Lower-Precision AI Traininghttps://developer.nvidia.com/blog/floating-point-8-an-introduction-to-efficient-lower-precision-ai-training/
Advanced Optimization Strategies for LLM Training on NVIDIA Grace Hopperhttps://developer.nvidia.com/blog/advanced-optimization-strategies-for-llm-training-on-nvidia-grace-hopper/
Stable and Scalable FP8 Deep Learning Training on Blackwell | GTC 2025https://www.nvidia.com/en-us/on-demand/session/gtc25-s72778/
Measure and Improve AI Workload Performance with NVIDIA DGX Cloud Benchmarkinghttps://developer.nvidia.com/blog/measure-and-improve-ai-workload-performance-with-nvidia-dgx-cloud-benchmarking/
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/docs/examples/comparison-fp8-bf16-training-nvidia-dgx-cloud-benchmarking-performance-explorer.jpg
Understanding the Language of Life's Biomolecules Across Evolution at a New Scale with Evo 2https://developer.nvidia.com/blog/understanding-the-language-of-lifes-biomolecules-across-evolution-at-a-new-scale-with-evo-2/
NVIDIA DGX Cloud Introduces Ready-To-Use Templates to Benchmark AI Platform Performancehttps://developer.nvidia.com/blog/nvidia-dgx-cloud-introduces-ready-to-use-templates-to-benchmark-ai-platform-performance/
Continued Pretraining of State-of-the-Art LLMs for Sovereign AI and Regulated Industries with iGenius and NVIDIA DGX Cloudhttps://developer.nvidia.com/blog/continued-pretraining-of-state-of-the-art-llms-for-sovereign-ai-and-regulated-industries-with-igenius-and-nvidia-dgx-cloud/
Developing a 172B LLM with Strong Japanese Capabilities Using NVIDIA Megatron-LMhttps://developer.nvidia.com/blog/developing-a-172b-llm-with-strong-japanese-capabilities-using-nvidia-megatron-lm/
How FP8 boosts LLM training by 18% on Amazon SageMaker P5 instanceshttps://aws.amazon.com/blogs/machine-learning/how-fp8-boosts-llm-training-by-18-on-amazon-sagemaker-p5-instances/
Efficiently train models with large sequence lengths using Amazon SageMaker model parallelhttps://aws.amazon.com/blogs/machine-learning/efficiently-train-models-with-large-sequence-lengths-using-amazon-sagemaker-model-parallel/
Reducing AI large model training costs by 30% requires just a single line of code from FP8 mixed precision training upgradeshttps://company.hpc-ai.com/blog/reducing-ai-large-model-training-costs-by-30-requires-just-a-single-line-of-code-from-fp8-mixed-precision-training-upgrades
Accelerating Transformers with NVIDIA cuDNN 9https://developer.nvidia.com/blog/accelerating-transformers-with-nvidia-cudnn-9/
Turbocharged Training: Optimizing the Databricks Mosaic AI stack with FP8https://www.databricks.com/blog/turbocharged-training-optimizing-databricks-mosaic-ai-stack-fp8
FP8 Training Support in SageMaker Model Parallelism Libraryhttps://docs.aws.amazon.com/sagemaker/latest/dg/model-parallel-release-notes.html
New NVIDIA NeMo Framework Features and NVIDIA H200https://developer.nvidia.com/blog/new-nvidia-nemo-framework-features-and-nvidia-h200-supercharge-llm-training-performance-and-versatility/
https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/blob/main/docs/examples/H200-NeMo-performance.png
Inflection-2: The Next Step Uphttps://inflection.ai/inflection-2
Unleashing The Power Of Transformers With NVIDIA Transformer Enginehttps://lambdalabs.com/blog/unleashing-the-power-of-transformers-with-nvidia-transformer-engine
Accelerating PyTorch Training Workloads with FP8https://towardsdatascience.com/accelerating-pytorch-training-workloads-with-fp8-5a5123aec7d7
Transformer Engine added to AWS DL Container for PyTorch Traininghttps://github.com/aws/deep-learning-containers/pull/3315
Breaking MLPerf Training Records with NVIDIA H100 GPUshttps://developer.nvidia.com/blog/breaking-mlperf-training-records-with-nvidia-h100-gpus/
Benchmarking Large Language Models on NVIDIA H100 GPUs with CoreWeave (Part 1)https://www.mosaicml.com/blog/coreweave-nvidia-h100-part-1
docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.htmlhttps://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html
python https://patch-diff.githubusercontent.com/topics/python
machine-learning https://patch-diff.githubusercontent.com/topics/machine-learning
deep-learning https://patch-diff.githubusercontent.com/topics/deep-learning
gpu https://patch-diff.githubusercontent.com/topics/gpu
cuda https://patch-diff.githubusercontent.com/topics/cuda
pytorch https://patch-diff.githubusercontent.com/topics/pytorch
jax https://patch-diff.githubusercontent.com/topics/jax
fp8 https://patch-diff.githubusercontent.com/topics/fp8
fp4 https://patch-diff.githubusercontent.com/topics/fp4
Readme https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#readme-ov-file
Apache-2.0 license https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#Apache-2.0-1-ov-file
Contributing https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#contributing-ov-file
Security policy https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine#security-ov-file
Please reload this pagehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Activityhttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/activity
Custom propertieshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/custom-properties
3.1k starshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/stargazers
35 watchinghttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/watchers
609 forkshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/forks
Report repository https://patch-diff.githubusercontent.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2FNVIDIA%2FTransformerEngine&report=NVIDIA+%28user%29
Releases 27https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/releases
v2.11 Latest Jan 15, 2026 https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/releases/tag/v2.11
+ 26 releaseshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/releases
Packages 0https://patch-diff.githubusercontent.com/orgs/NVIDIA/packages?repo_name=TransformerEngine
Please reload this pagehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Please reload this pagehttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine
Contributors 149https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/graphs/contributors
https://github.com/ksivaman
https://github.com/timmoon10
https://github.com/apps/pre-commit-ci
https://github.com/phu0ngng
https://github.com/ptrendx
https://github.com/cyanguwa
https://github.com/jberchtold-nvidia
https://github.com/pggPL
https://github.com/yaox12
https://github.com/zlsh80826
https://github.com/denera
https://github.com/mingxu1067
https://github.com/xrennvidia
https://github.com/KshitijLakhani
+ 135 contributorshttps://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/graphs/contributors
Python 56.1% https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/search?l=python
Cuda 26.9% https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/search?l=cuda
C++ 14.4% https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/search?l=c%2B%2B
C 2.0% https://patch-diff.githubusercontent.com/NVIDIA/TransformerEngine/search?l=c
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width


URLs of crawlers that visited me.