NVIDIA / TransformerEngineLinks
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.
☆3,132Updated this 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☆4,853Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,657Updated last week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,600Updated last year
- Transformer related optimization, including BERT, GPT☆6,392Updated last year
- A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresse…☆1,925Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,431Updated 6 months ago
- Tile primitives for speedy kernels☆3,120Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,092Updated 7 months ago
- Pipeline Parallelism for PyTorch☆784Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,224Updated 5 months ago
- PyTorch extensions for high performance and large scale training.☆3,397Updated 9 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,859Updated last week
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,577Updated last week
- A PyTorch native platform for training generative AI models☆5,023Updated last week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,249Updated last year
- Minimalistic large language model 3D-parallelism training☆2,529Updated last month
- The Triton TensorRT-LLM Backend☆918Updated this week
- Puzzles for learning Triton☆2,283Updated last year
- NCCL Tests☆1,423Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,332Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,242Updated 5 months ago
- Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4☆962Updated last month
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,352Updated this week
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆921Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,104Updated last week
- Microsoft Automatic Mixed Precision Library☆635Updated 2 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,705Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,316Updated 11 months ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,525Updated this week
- 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…☆1,587Updated last week