NVIDIA / TransformerEngineLinks
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
☆2,763Updated last week
Alternatives and similar repositories for TransformerEngine
Users that are interested in TransformerEngine are comparing it to the libraries listed below
Sorting:
- FlashInfer: Kernel Library for LLM Serving☆3,861Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,392Updated last week
- Transformer related optimization, including BERT, GPT☆6,320Updated last year
- A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …☆1,431Updated last week
- Tile primitives for speedy kernels☆2,803Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,516Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,289Updated 2 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,166Updated 2 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,836Updated last week
- Pipeline Parallelism for PyTorch☆780Updated last year
- PyTorch extensions for high performance and large scale training.☆3,380Updated 5 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,063Updated 3 months ago
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,508Updated this week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,196Updated last year
- The Triton TensorRT-LLM Backend☆897Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆1,877Updated this week
- Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4☆928Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,152Updated last week
- Minimalistic large language model 3D-parallelism training☆2,252Updated last month
- A pytorch quantization backend for optimum☆991Updated last month
- NCCL Tests☆1,284Updated last week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆3,508Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,062Updated last year
- Puzzles for learning Triton☆2,031Updated 10 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,142Updated last month
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆879Updated last week
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,449Updated this week
- Flash Attention in ~100 lines of CUDA (forward pass only)☆941Updated 9 months ago
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,584Updated last year
- A PyTorch Native LLM Training Framework☆874Updated last month