Alternatives and similar repositories for transformer-deploy

Users that are interested in transformer-deploy are comparing it to the libraries listed below

• ELS-RD / kernl
  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…
  ☆1,575Updated last year
• Ki6an / fastT5
  ⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
  ☆581Updated 2 years ago
• Tencent / TurboTransformers
  a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
  ☆1,526Updated 3 months ago
• bigscience-workshop / bigscience
  Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.
  ☆1,001Updated 11 months ago
• tunib-ai / parallelformers
  Parallelformers: An Efficient Model Parallelization Toolkit for Deployment
  ☆790Updated 2 years ago
• facebookresearch / bitsandbytes
  Library for 8-bit optimizers and quantization routines.
  ☆716Updated 2 years ago
• microsoft / fastformers
  FastFormers - highly efficient transformer models for NLU
  ☆705Updated 3 months ago
• deepspeedai / DeepSpeed-MII
  MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
  ☆2,026Updated last week
• facebookresearch / fairscale
  PyTorch extensions for high performance and large scale training.
  ☆3,337Updated 2 months ago
• triton-inference-server / pytriton
  PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.
  ☆804Updated last week
• triton-inference-server / python_backend
  Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.
  ☆622Updated this week
• huggingface / optimum
  🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…
  ☆2,967Updated last week
• triton-inference-server / fastertransformer_backend
  ☆411Updated last year
• huggingface / transformers-bloom-inference
  Fast Inference Solutions for BLOOM
  ☆564Updated 9 months ago
• bigscience-workshop / Megatron-DeepSpeed
  Ongoing research training transformer language models at scale, including: BERT & GPT-2
  ☆1,401Updated last year
• huggingface / nn_pruning
  Prune a model while finetuning or training.
  ☆403Updated 3 years ago
• pytorch / torchdynamo
  A Python-level JIT compiler designed to make unmodified PyTorch programs faster.
  ☆1,053Updated last year
• criteo / autofaiss
  Automatically create Faiss knn indices with the most optimal similarity search parameters.
  ☆862Updated last year
• ShannonAI / service-streamer
  Boosting your Web Services of Deep Learning Applications.
  ☆1,241Updated 4 years ago
• JonasGeiping / cramming
  Cramming the training of a (BERT-type) language model into limited compute.
  ☆1,338Updated last year
• Lightning-Universe / lightning-transformers
  Flexible components pairing 🤗 Transformers with Pytorch Lightning
  ☆609Updated 2 years ago
• neuralmagic / deepsparse
  Sparsity-aware deep learning inference runtime for CPUs
  ☆3,157Updated last month
• triton-inference-server / model_analyzer
  Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…
  ☆479Updated last month
• NVIDIA / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆6,231Updated last year
• lucidrains / RETRO-pytorch
  Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
  ☆868Updated last year
• huggingface / evaluate
  🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
  ☆2,254Updated 3 weeks ago
• triton-inference-server / tensorrtllm_backend
  The Triton TensorRT-LLM Backend
  ☆859Updated this week
• triton-inference-server / tutorials
  This repository contains tutorials and examples for Triton Inference Server
  ☆732Updated last month
• google-research / deduplicate-text-datasets
  ☆1,227Updated 11 months ago
• BlackSamorez / tensor_parallel
  Automatically split your PyTorch models on multiple GPUs for training & inference
  ☆656Updated last year