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.
☆2,567Updated 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☆3,409Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,456Updated last year
- PyTorch native quantization and sparsity for training and inference☆2,207Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,172Updated last week
- A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …☆1,068Updated last week
- Transformer related optimization, including BERT, GPT☆6,255Updated last year
- Tile primitives for speedy kernels☆2,532Updated this week
- Pipeline Parallelism for PyTorch☆772Updated 11 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,809Updated last week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,117Updated last week
- PyTorch extensions for high performance and large scale training.☆3,346Updated 3 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,040Updated 3 weeks ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,148Updated last year
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,454Updated this week
- NCCL Tests☆1,192Updated 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…☆1,578Updated last year
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek/Kimi-K2/Qwen3 FP8/FP4☆868Updated this week
- The Triton TensorRT-LLM Backend☆866Updated last week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,419Updated 2 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,456Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,056Updated last year
- Microsoft Automatic Mixed Precision Library☆616Updated 9 months ago
- Minimalistic large language model 3D-parallelism training☆2,051Updated 2 weeks ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,664Updated last week
- Puzzles for learning Triton☆1,769Updated 8 months ago
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆840Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,260Updated 4 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆863Updated 10 months ago
- A pytorch quantization backend for optimum☆968Updated 3 weeks ago
- Provides end-to-end model development pipelines for LLMs and Multimodal models that can be launched on-prem or cloud-native.☆506Updated 3 months ago