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.
☆3,407Aug 8, 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☆3,645Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,129Updated 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…☆3,483Updated 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…☆14,335Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆7,707Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- PyTorch native quantization and sparsity for training and inference☆2,932Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,214Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,056Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,535Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆796Aug 14, 2025Updated 11 months ago
- High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI☆497Jul 31, 2026Updated last week
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆13,233Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,123Sep 4, 2024Updated last year
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,632Jul 20, 2026Updated 2 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,161Updated this week
- Tile primitives for speedy kernels☆3,616Jul 13, 2026Updated 3 weeks ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,499Feb 20, 2026Updated 5 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆88,524Updated this week
- Transformer related optimization, including BERT, GPT☆6,446Mar 27, 2024Updated 2 years ago
- Fast and memory-efficient exact attention☆24,654Updated this week
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,605Jan 17, 2026Updated 6 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,414Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,609Jul 17, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- The Triton TensorRT-LLM Backend☆941Jul 22, 2026Updated 2 weeks ago
- Development repository for the Triton language and compiler☆19,898Updated this week
- LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM…☆1,222Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,205Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,524Updated this week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,986Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆312Updated this week
- A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support…☆1,558Updated this week
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,733Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Fast low-bit matmul kernels in Triton☆480Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆852Mar 6, 2025Updated last year
- Scalable toolkit for efficient model reinforcement☆1,890Updated this week
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,814Mar 28, 2024Updated 2 years ago
- Distributed Compiler based on Triton for Parallel Systems☆1,511Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,674Jul 12, 2024Updated 2 years ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,069Updated this week