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.
☆1,573Updated 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.☆1,053Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,516Updated this week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,130Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,025Updated this week
- Pipeline Parallelism for PyTorch☆769Updated 10 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,433Updated 11 months ago
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,686Updated 8 months ago
- PyTorch extensions for high performance and large scale training.☆3,336Updated 2 months ago
- An open-source efficient deep learning framework/compiler, written in python.☆703Updated 2 weeks ago
- Library for 8-bit optimizers and quantization routines.☆716Updated 2 years ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,336Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,258Updated 3 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,397Updated last year
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,647Updated 3 months ago
- maximal update parametrization (µP)☆1,549Updated 11 months ago
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆1,000Updated 11 months ago
- A pytorch quantization backend for optimum☆958Updated 2 weeks ago
- ☆543Updated 6 months ago
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,953Updated this week
- Foundation Architecture for (M)LLMs☆3,081Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆962Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆693Updated 10 months ago
- PyTorch native quantization and sparsity for training and inference☆2,138Updated this week
- Transformer related optimization, including BERT, GPT☆6,224Updated last year
- Parallelformers: An Efficient Model Parallelization Toolkit for Deployment☆790Updated 2 years ago
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek FP8/FP4☆848Updated this week
- ☆411Updated last year
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,435Updated this week
- Fast Inference Solutions for BLOOM☆564Updated 8 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,113Updated 3 weeks ago