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.
☆1,564Updated 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.☆1,040Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,002Updated last month
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,381Updated this week
- Library for 8-bit optimizers and quantization routines.☆716Updated 2 years ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,392Updated 9 months ago
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,684Updated 6 months ago
- Training and serving large-scale neural networks with auto parallelization.☆3,125Updated last year
- Pipeline Parallelism for PyTorch☆764Updated 8 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆863Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,331Updated 10 months ago
- maximal update parametrization (µP)☆1,498Updated 9 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,093Updated last year
- An open-source efficient deep learning framework/compiler, written in python.☆698Updated 2 months ago
- PyTorch extensions for high performance and large scale training.☆3,306Updated 2 weeks ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆686Updated 8 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,386Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,242Updated last month
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek FP8/FP4☆803Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,054Updated 11 months ago
- Transformer related optimization, including BERT, GPT☆6,137Updated last year
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,630Updated 3 weeks ago
- Parallelformers: An Efficient Model Parallelization Toolkit for Deployment☆786Updated 2 years ago
- Automatically split your PyTorch models on multiple GPUs for training & inference☆652Updated last year
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆992Updated 8 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,785Updated this week
- Microsoft Automatic Mixed Precision Library☆593Updated 6 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆6,949Updated this week
- PyTorch native quantization and sparsity for training and inference☆1,996Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,942Updated last week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,867Updated this week