Transformer related optimization, including BERT, GPT
☆6,446Mar 27, 2024Updated 2 years ago
Alternatives and similar repositories for FasterTransformer
Users that are interested in FasterTransformer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,613Updated this week
- Fast and memory-efficient exact attention☆24,905Updated this week
- Ongoing research training transformer models at scale☆17,894Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,533Updated this week
- Development repository for the Triton language and compiler☆20,157Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,430Sep 8, 2026Updated last week
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,294May 16, 2023Updated 3 years ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆43,107Updated this week
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆13,344Updated this week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,546Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,404Updated this week
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆10,986Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆8,477Sep 7, 2026Updated last week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,289Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,634Jul 17, 2025Updated last year
- Large Language Model Text Generation Inference☆10,887Mar 21, 2026Updated 5 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆8,070Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,113Jun 30, 2025Updated last year
- a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.☆1,551Jul 18, 2025Updated last year
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,725Aug 7, 2026Updated last month
- Open Machine Learning Compiler Framework☆13,744Updated this week
- PyTorch extensions for high performance and large scale training.☆3,406Apr 26, 2025Updated last year
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆479Mar 15, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,899Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,263Aug 14, 2025Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,685Jul 12, 2024Updated 2 years ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,369Mar 27, 2024Updated 2 years ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆35,950Updated this week
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆8,999Sep 7, 2026Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆91,730Updated this week
- ☆414Nov 11, 2023Updated 2 years ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,993Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Running BERT without Padding☆479Mar 18, 2022Updated 4 years ago
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,348Oct 28, 2024Updated last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,771Jun 25, 2024Updated 2 years ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,070Apr 11, 2025Updated last year
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆21,673Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,565Updated this week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,866Updated this week