A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
☆2,676May 16, 2026Updated this week
Alternatives and similar repositories for Model-Optimizer
Users that are interested in Model-Optimizer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆13,669Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,621Updated 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…☆3,340Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,217May 12, 2026Updated last week
- PyTorch native quantization and sparsity for training and inference☆2,825Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The Triton TensorRT-LLM Backend☆934May 7, 2026Updated last week
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆12,977Apr 13, 2026Updated last month
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,076Sep 4, 2024Updated last year
- Experimental projects related to TensorRT☆125May 8, 2026Updated last week
- Transformer related optimization, including BERT, GPT☆6,416Mar 27, 2024Updated 2 years ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆838Mar 6, 2025Updated last year
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,796Mar 28, 2024Updated 2 years ago
- A simple tool that can generate TensorRT plugin code quickly.☆241Jul 11, 2023Updated 2 years ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,964Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,536Jul 17, 2025Updated 10 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆783Aug 14, 2025Updated 9 months ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,731May 13, 2026Updated last week
- A Datacenter Scale Distributed Inference Serving Framework☆6,791Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆27,836Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,647Jul 12, 2024Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,343Feb 20, 2026Updated 3 months ago
- TensorRT Plugin Autogen Tool☆368Apr 7, 2023Updated 3 years ago
- Fast and memory-efficient exact attention☆23,836Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A pytorch quantization backend for optimum☆1,040Apr 2, 2026Updated last month
- Development repository for the Triton language and compiler☆19,184Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,214Apr 20, 2026Updated last month
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,061Updated this week
- Tile primitives for speedy kernels☆3,360May 11, 2026Updated last week
- ☆210May 5, 2025Updated last year
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆10,657Updated this week
- Simple samples for TensorRT programming☆1,659May 5, 2026Updated 2 weeks ago
- Fast low-bit matmul kernels in Triton☆454Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,336May 11, 2025Updated last year
- Applied AI experiments and examples for PyTorch☆321Aug 22, 2025Updated 8 months ago
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆10,965May 3, 2026Updated 2 weeks ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆508Nov 26, 2024Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,858Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,636Updated this week
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,372Jan 17, 2026Updated 4 months ago