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.
☆2,516Updated 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☆3,273Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,113Updated 3 weeks ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,433Updated 11 months ago
- PyTorch native quantization and sparsity for training and inference☆2,138Updated this week
- Transformer related optimization, including BERT, GPT☆6,224Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,130Updated last year
- A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …☆1,025Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,025Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,096Updated 3 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,200Updated last month
- Tile primitives for speedy kernels☆2,489Updated last week
- Pipeline Parallelism for PyTorch☆769Updated 10 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,259Updated 3 months ago
- PyTorch extensions for high performance and large scale training.☆3,336Updated 2 months ago
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆1,464Updated last week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,805Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆848Updated 10 months ago
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek FP8/FP4☆848Updated this week
- A pytorch quantization backend for optimum☆959Updated 2 weeks 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…☆1,573Updated last year
- Microsoft Automatic Mixed Precision Library☆611Updated 9 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,336Updated last week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,587Updated this week
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆824Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,345Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,053Updated last year
- Puzzles for learning Triton☆1,737Updated 7 months ago
- The Triton TensorRT-LLM Backend☆858Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,348Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆834Updated last month