ELS-RD / transformer-deploy
Efficient, scalable and enterprise-grade CPU/GPU inference server for π€ Hugging Face transformer models π
β1,683Updated 6 months ago
Alternatives and similar repositories for transformer-deploy:
Users that are interested in transformer-deploy are comparing it to the libraries listed below
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackabβ¦β1,566Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.β2,009Updated last month
- Library for 8-bit optimizers and quantization routines.β716Updated 2 years ago
- PyTorch extensions for high performance and large scale training.β3,309Updated last week
- π Accelerate inference and training of π€ Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimizationβ¦β2,874Updated last week
- β‘ boost inference speed of T5 models by 5x & reduce the model size by 3x.β578Updated 2 years ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2β1,386Updated last year
- FastFormers - highly efficient transformer models for NLUβ706Updated last month
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.β993Updated 9 months ago
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.β1,042Updated last year
- Fast Inference Solutions for BLOOMβ561Updated 6 months ago
- Automatically create Faiss knn indices with the most optimal similarity search parameters.β853Updated 11 months ago
- Parallelformers: An Efficient Model Parallelization Toolkit for Deploymentβ786Updated 2 years ago
- a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.β1,520Updated last month
- Transformer related optimization, including BERT, GPTβ6,147Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blaβ¦β2,393Updated this week
- π€ Evaluate: A library for easily evaluating machine learning models and datasets.β2,199Updated 3 months ago
- Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.β606Updated this week
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.β790Updated 2 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2β2,064Updated last month
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".β2,099Updated last year
- β411Updated last year
- Prune a model while finetuning or training.β402Updated 2 years ago
- Efficient few-shot learning with Sentence Transformersβ2,477Updated 3 weeks ago
- β1,513Updated last week
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorchβ864Updated last year
- Flexible components pairing π€ Transformers with Pytorch Lightningβ608Updated 2 years ago
- Automatically split your PyTorch models on multiple GPUs for training & inferenceβ651Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.β1,331Updated 10 months ago
- β1,208Updated 9 months ago