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.
☆3,823Sep 18, 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☆3,795Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,443Updated 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…☆3,540Updated 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…☆14,652Updated this week
- PyTorch native quantization for training and inference☆2,980Updated 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.
- A Datacenter Scale Distributed Inference Serving Framework☆8,114Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,177Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,453Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,140Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆802Aug 14, 2025Updated last year
- High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI☆561Sep 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…☆13,355Sep 10, 2026Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,148Sep 4, 2024Updated 2 years ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,431Updated 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.
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,845Updated this week
- Tile primitives for speedy kernels☆3,716Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,536Feb 20, 2026Updated 6 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆92,107Updated this week
- Transformer related optimization, including BERT, GPT☆6,447Mar 27, 2024Updated 2 years ago
- Fast and memory-efficient exact attention☆24,966Updated this week
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,801Jan 17, 2026Updated 8 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,503Sep 12, 2026Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,636Jul 17, 2025Updated last year
- 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.
- The Triton TensorRT-LLM Backend☆944Updated this week
- Development repository for the Triton language and compiler☆20,190Updated this week
- LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM…☆1,257Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,606Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,764Updated this week
- A SOTA quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的量化工具包☆1,619Updated this week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,995Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆326Updated this week
- Open sources book with Modern CUDA Learn Notes for Beginners, includes FP16/BF16, FP8, HGEMM, FlashAttention, CuTe, etc.☆11,979Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Fast low-bit matmul kernels in Triton☆485Aug 9, 2026Updated last month
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆861Mar 6, 2025Updated last year
- Scalable toolkit for efficient model reinforcement☆2,025Updated this week
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,822Mar 28, 2024Updated 2 years ago
- Distributed Compiler and Optimized Parallel Kernels☆1,546Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,685Jul 12, 2024Updated 2 years ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,862Updated this week