🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
☆329Sep 25, 2025Updated 5 months ago
Alternatives and similar repositories for optimum-benchmark
Users that are interested in optimum-benchmark are comparing it to the libraries listed below
Sorting:
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" given…☆15Oct 16, 2023Updated 2 years ago
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆3,305Feb 9, 2026Updated 3 weeks ago
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆32Sep 19, 2025Updated 5 months ago
- The backend behind the LLM-Perf Leaderboard☆11May 5, 2024Updated last year
- Easy and Efficient Quantization for Transformers☆206Jan 28, 2026Updated last month
- A pytorch quantization backend for optimum☆1,025Nov 21, 2025Updated 3 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,315May 11, 2025Updated 9 months ago
- This repository contains the experimental PyTorch native float8 training UX☆226Aug 1, 2024Updated last year
- Build compute kernels and load them from the Hub.☆452Updated this week
- ☆24Updated this week
- LLMPerf is a library for validating and benchmarking LLMs☆1,091Dec 9, 2024Updated last year
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,314Feb 20, 2026Updated last week
- PyTorch native quantization and sparsity for training and inference☆2,707Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,095Jun 30, 2025Updated 8 months ago
- ☆1,030Feb 6, 2025Updated last year
- Large Language Model Text Generation Inference☆10,788Jan 8, 2026Updated last month
- Minimalistic large language model 3D-parallelism training☆2,579Feb 19, 2026Updated last week
- 👷 Build compute kernels☆216Jan 27, 2026Updated last month
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,443Jul 17, 2025Updated 7 months ago
- A blazing fast inference solution for text embeddings models☆4,525Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,315Mar 6, 2025Updated 11 months ago
- Robust recipes to align language models with human and AI preferences☆5,506Sep 8, 2025Updated 5 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆7,997Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,176Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,025Sep 4, 2024Updated last year
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆219Feb 16, 2026Updated 2 weeks ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆282Jul 11, 2024Updated last year
- ☆71Mar 26, 2025Updated 11 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆913Dec 18, 2025Updated 2 months ago
- 🤗 Optimum ONNX: Export your model to ONNX and run inference with ONNX Runtime☆119Feb 19, 2026Updated last week
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- A framework for few-shot evaluation of language models.☆11,478Feb 15, 2026Updated 2 weeks ago
- Training and inference on AWS Trainium and Inferentia chips.☆261Updated this week
- Experiment of using Tangent to autodiff triton☆82Jan 22, 2024Updated 2 years ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆256Updated this week
- Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…☆506Feb 17, 2026Updated last week
- IBM development fork of https://github.com/huggingface/text-generation-inference☆63Sep 18, 2025Updated 5 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆712Aug 13, 2024Updated last year
- Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.☆161Apr 3, 2024Updated last year