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…
  ☆1,586Updated last year
• bigscience-workshop / bigscience
  Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.
  ☆1,005Updated last year
• Ki6an / fastT5
  ⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
  ☆587Updated 2 years ago
• Tencent / TurboTransformers
  a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
  ☆1,532Updated 3 months ago
• huggingface / optimum
  🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…
  ☆3,115Updated last week
• facebookresearch / bitsandbytes
  Library for 8-bit optimizers and quantization routines.
  ☆779Updated 3 years ago
• tunib-ai / parallelformers
  Parallelformers: An Efficient Model Parallelization Toolkit for Deployment
  ☆790Updated 2 years ago
• facebookresearch / fairscale
  PyTorch extensions for high performance and large scale training.
  ☆3,380Updated 5 months ago
• triton-inference-server / pytriton
  PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.
  ☆823Updated 2 months ago
• bigscience-workshop / Megatron-DeepSpeed
  Ongoing research training transformer language models at scale, including: BERT & GPT-2
  ☆1,422Updated last year
• deepspeedai / DeepSpeed-MII
  MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
  ☆2,067Updated 3 months ago
• microsoft / fastformers
  FastFormers - highly efficient transformer models for NLU
  ☆707Updated 7 months ago
• huggingface / transformers-bloom-inference
  Fast Inference Solutions for BLOOM
  ☆565Updated last year
• huggingface / nn_pruning
  Prune a model while finetuning or training.
  ☆405Updated 3 years ago
• triton-inference-server / python_backend
  Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.
  ☆648Updated last week
• triton-inference-server / fastertransformer_backend
  ☆413Updated last year
• pytorch / torchdynamo
  A Python-level JIT compiler designed to make unmodified PyTorch programs faster.
  ☆1,062Updated last year
• 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…
  ☆494Updated last week
• JonasGeiping / cramming
  Cramming the training of a (BERT-type) language model into limited compute.
  ☆1,348Updated last year
• NVIDIA / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆6,326Updated last year
• facebookresearch / cc_net
  Tools to download and cleanup Common Crawl data
  ☆1,031Updated 2 years ago
• criteo / autofaiss
  Automatically create Faiss knn indices with the most optimal similarity search parameters.
  ☆872Updated last year
• Lightning-Universe / lightning-transformers
  Flexible components pairing 🤗 Transformers with Pytorch Lightning
  ☆612Updated 2 years ago
• BlackSamorez / tensor_parallel
  Automatically split your PyTorch models on multiple GPUs for training & inference
  ☆657Updated last year
• ShannonAI / service-streamer
  Boosting your Web Services of Deep Learning Applications.
  ☆1,245Updated 4 years ago
• huggingface / evaluate
  🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
  ☆2,340Updated 3 weeks ago
• Muennighoff / sgpt
  SGPT: GPT Sentence Embeddings for Semantic Search
  ☆875Updated last year
• triton-inference-server / client
  Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.
  ☆652Updated last week
• IST-DASLab / gptq
  Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
  ☆2,202Updated last year
• microsoft / mup
  maximal update parametrization (µP)
  ☆1,611Updated last year