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.
☆3,478Aug 6, 2026Updated this week
Alternatives and similar repositories for TransformerEngine
Users that are interested in TransformerEngine are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- FlashInfer: Kernel Library for LLM Serving☆6,110Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,205Updated this week
- Transformer related optimization, including BERT, GPT☆6,447Mar 27, 2024Updated 2 years ago
- Ongoing research training transformer models at scale☆17,340Updated this week
- Fast and memory-efficient exact attention☆24,644Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Distributed Compiler based on Triton for Parallel Systems☆1,508Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,352Aug 28, 2025Updated 11 months ago
- Development repository for the Triton language and compiler☆19,869Updated this week
- Tile primitives for speedy kernels☆3,612Jul 13, 2026Updated 3 weeks ago
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,631Jul 20, 2026Updated 2 weeks ago
- Microsoft Automatic Mixed Precision Library☆635Dec 1, 2025Updated 8 months ago
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,316Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,932Updated this week
- A Quirky Assortment of CuTe Kernels☆1,091Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A PyTorch native platform for training generative AI models☆5,593Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆737Jul 4, 2026Updated last month
- 🚀 Efficient implementations for emerging model architectures☆5,512Updated this week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,537Jul 15, 2026Updated 3 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,139Updated this week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆3,397Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,258Aug 14, 2025Updated 11 months ago
- Ring attention implementation with flash attention☆1,044Sep 10, 2025Updated 10 months ago
- Minimalistic large language model 3D-parallelism training☆2,775May 26, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,418Updated this week
- Efficient Triton Kernels for LLM Training☆6,554Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆8,394Jul 29, 2026Updated last week
- PyTorch extensions for high performance and large scale training.☆3,409Apr 26, 2025Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆896Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,122Sep 4, 2024Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,189Updated this week
- Perplexity GPU Kernels☆598Nov 7, 2025Updated 9 months ago
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆849Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Optimized primitives for collective multi-GPU communication☆4,950Updated this week
- A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Auto…☆17,924Updated this week
- DeepEP: an efficient expert-parallel communication library☆9,960Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,129Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,605Jul 17, 2025Updated last year
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,210Updated this week
- Zero Bubble Pipeline Parallelism☆464May 7, 2025Updated last year