ELS-RD / kernlLinks
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.
☆1,585Updated last year
Alternatives and similar repositories for kernl
Users that are interested in kernl are comparing it to the libraries listed below
Sorting:
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,066Updated last year
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,689Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,073Updated 4 months ago
- Library for 8-bit optimizers and quantization routines.☆780Updated 3 years ago
- Pipeline Parallelism for PyTorch☆780Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,350Updated last year
- An open-source efficient deep learning framework/compiler, written in python.☆733Updated 2 months ago
- maximal update parametrization (µP)☆1,613Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,212Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,883Updated this week
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆1,006Updated last year
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,841Updated this week
- PyTorch extensions for high performance and large scale training.☆3,385Updated 6 months ago
- Training and serving large-scale neural networks with auto parallelization.☆3,160Updated last year
- Parallelformers: An Efficient Model Parallelization Toolkit for Deployment☆790Updated 2 years ago
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,689Updated last week
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆977Updated last year
- A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.☆1,231Updated this week
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆875Updated 2 years ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,543Updated last year
- Automatically split your PyTorch models on multiple GPUs for training & inference☆658Updated last year
- Foundation Architecture for (M)LLMs☆3,119Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,425Updated last year
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆883Updated last week
- A pytorch quantization backend for optimum☆1,004Updated 2 weeks ago
- Fast Inference Solutions for BLOOM☆565Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,110Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,295Updated 8 months ago
- ☆413Updated last year
- PyTorch native quantization and sparsity for training and inference☆2,489Updated this week