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.
☆1,557Updated last year
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.☆1,032Updated 10 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,044Updated 11 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆2,233Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,974Updated this week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,761Updated this week
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,680Updated 4 months ago
- Pipeline Parallelism for PyTorch☆753Updated 6 months ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,320Updated 8 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,368Updated 11 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,353Updated 7 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,786Updated 3 weeks ago
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,791Updated last week
- Library for 8-bit optimizers and quantization routines.☆718Updated 2 years ago
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,608Updated 2 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆857Updated last year
- PyTorch extensions for high performance and large scale training.☆3,269Updated last month
- An open-source efficient deep learning framework/compiler, written in python.☆683Updated this week
- Parallelformers: An Efficient Model Parallelization Toolkit for Deployment☆785Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,200Updated 4 months ago
- A pytorch quantization backend for optimum☆891Updated last month
- Fast Inference Solutions for BLOOM☆563Updated 4 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆679Updated 6 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,002Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,033Updated 9 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆742Updated 5 months ago
- Transformer related optimization, including BERT, GPT☆6,054Updated 11 months ago
- 4 bits quantization of LLaMA using GPTQ☆3,042Updated 7 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆6,744Updated this week
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆949Updated last year
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆985Updated 7 months ago