A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
☆3,262Jul 19, 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:
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,561Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,983Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat …☆14,158Updated 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…☆3,434Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,906Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,104Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆996Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆30,498Updated this week
- High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI☆480Jul 3, 2026Updated 2 weeks ago
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆13,164Jul 7, 2026Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,109Sep 4, 2024Updated last year
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,667Updated this week
- Fast and memory-efficient exact attention☆24,489Updated this week
- Transformer related optimization, including BERT, GPT☆6,439Mar 27, 2024Updated 2 years ago
- 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.
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,491Jan 17, 2026Updated 6 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,377Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,591Jul 17, 2025Updated last year
- The Triton TensorRT-LLM Backend☆939Updated this week
- Development repository for the Triton language and compiler☆19,725Updated this week
- LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM…☆1,208Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,367Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆794Aug 14, 2025Updated 11 months ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,977Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support…☆1,527Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆302Updated this week
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆11,578Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆850Mar 6, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆86,634Updated this week
- Scalable toolkit for efficient model reinforcement☆1,832Updated this week
- Tile primitives for speedy kernels☆3,550Jul 13, 2026Updated last week
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,806Mar 28, 2024Updated 2 years ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,669Jul 12, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆10,706Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,468Feb 20, 2026Updated 5 months ago
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆10,853Updated this week
- Ongoing research training transformer models at scale☆17,108Updated this week
- Efficient Triton Kernels for LLM Training☆6,521Updated this week
- A pytorch quantization backend for optimum☆1,046Updated this week
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,118Updated this week