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 hackable.
☆1,550Updated 11 months ago
Alternatives and similar repositories for kernl:
Users that are interested in kernl are comparing it to the libraries listed below
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,019Updated 9 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆2,115Updated this week
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,673Updated 3 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,006Updated 10 months ago
- Pipeline Parallelism for PyTorch☆739Updated 5 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,948Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,320Updated 6 months ago
- Library for 8-bit optimizers and quantization routines.☆717Updated 2 years ago
- An open-source efficient deep learning framework/compiler, written in python.☆672Updated last week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,695Updated this week
- Cramming the training of a (BERT-type) language model into limited compute.☆1,311Updated 7 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆990Updated 5 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆857Updated last year
- Parallelformers: An Efficient Model Parallelization Toolkit for Deployment☆781Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,358Updated 10 months ago
- PyTorch extensions for high performance and large scale training.☆3,235Updated 2 weeks ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,750Updated this week
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆945Updated last year
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆982Updated 6 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,183Updated 3 months ago
- Tutel MoE: An Optimized Mixture-of-Experts Implementation☆750Updated last week
- Fast Inference Solutions for BLOOM☆563Updated 3 months ago
- Minimalistic large language model 3D-parallelism training☆1,400Updated this week
- Microsoft Automatic Mixed Precision Library☆553Updated 4 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆669Updated 5 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,076Updated last year
- maximal update parametrization (µP)☆1,438Updated 6 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆689Updated 4 months ago
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,590Updated last month
- Serving multiple LoRA finetuned LLM as one☆1,018Updated 8 months ago