NVIDIA / TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
☆1,979Updated this week
Related projects ⓘ
Alternatives and complementary repositories for TransformerEngine
- FlashInfer: Kernel Library for LLM Serving☆1,452Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,526Updated last month
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,257Updated 4 months ago
- Pipeline Parallelism for PyTorch☆726Updated 2 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,904Updated this week
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆1,713Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,893Updated last month
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆1,941Updated 7 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…☆1,535Updated 9 months ago
- PyTorch extensions for high performance and large scale training.☆3,195Updated last week
- Microsoft Automatic Mixed Precision Library☆525Updated last month
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,011Updated 7 months ago
- Transformer related optimization, including BERT, GPT☆5,890Updated 7 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,149Updated last month
- TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillati…☆567Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,227Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,338Updated 8 months ago
- A pytorch quantization backend for optimum☆824Updated last week
- The Triton TensorRT-LLM Backend☆706Updated this week
- PyTorch native quantization and sparsity for training and inference☆1,585Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆1,765Updated this week
- 🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools☆2,576Updated this week
- Tutel MoE: An Optimized Mixture-of-Experts Implementation☆735Updated this week
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆734Updated this week
- Tile primitives for speedy kernels☆1,658Updated this week
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,210Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆6,299Updated this week
- Ring attention implementation with flash attention☆585Updated last week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆2,613Updated this week