Optimized local inference for LLMs with HuggingFace-like APIs for quantization, vision/language models, multimodal agents, speech, vector DB, and RAG.
☆382Oct 18, 2024Updated last year
Alternatives and similar repositories for NanoLLM
Users that are interested in NanoLLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Zero-copy multimodal vector DB with CUDA and CLIP/SigLIP☆66May 6, 2025Updated last year
- Machine Learning Containers for NVIDIA Jetson and JetPack-L4T☆4,869Aug 10, 2026Updated last month
- A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson☆250Nov 14, 2023Updated 2 years ago
- GitHub repo for Jetson AI Lab☆208Updated this week
- A project that optimizes Whisper for low latency inference using NVIDIA TensorRT☆113Oct 15, 2024Updated last year
- 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.
- A collection of reference AI microservices and workflows for Jetson Platform Services☆61Jan 28, 2025Updated last year
- ROS2 nodes for LLM, VLM, VLA☆198Aug 16, 2024Updated 2 years ago
- C++/CUDA/Python multimedia utilities for NVIDIA Jetson☆911Oct 16, 2025Updated 11 months ago
- This repository provides YOLOV5 GPU optimization sample☆108Jan 6, 2023Updated 3 years ago
- Gemma models running 100% local on an 8 GB Jetson Orin Nano: voice assistants with RAG, multi-agent NPCs, live EN-JA translation, and a G…☆82Apr 17, 2026Updated 5 months ago
- Hosting a tutorial documentation for running Isaac ROS Visual SLAM on Jetson device.☆26Feb 28, 2024Updated 2 years ago
- ONNX and TensorRT implementation of Whisper☆69May 27, 2023Updated 3 years ago
- A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.☆524Feb 6, 2025Updated last year
- A project demonstrating how to make DeepStream docker images.☆97Aug 19, 2026Updated last month
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…☆3,864Mar 12, 2026Updated 6 months ago
- A utility library to help integrate Python applications with Metropolis Microservices for Jetson☆16Dec 21, 2024Updated last year
- ☆30Nov 16, 2024Updated last year
- llm deploy project based onnx.☆49Oct 9, 2024Updated last year
- 8-bit CUDA functions for PyTorch, modified to build on Jetson Xavier☆15Apr 26, 2023Updated 3 years ago
- Deploying LLMs offline on the NVIDIA Jetson platform marks the dawn of a new era in embodied intelligence, where devices can function ind…☆106Mar 23, 2024Updated 2 years ago
- NVIDIA DLA-SW, the recipes and tools for running deep learning workloads on NVIDIA DLA cores for inference applications.☆236Aug 23, 2026Updated last month
- High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI☆570Sep 3, 2026Updated 3 weeks ago
- Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.☆9,003Oct 16, 2025Updated 11 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- deepstream_tools will serve as a parent repo to hold various tools to be released for DeepStream SDK.☆34Jul 15, 2026Updated 2 months ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆63Nov 8, 2024Updated last year
- This repository provides optical character detection and recognition solution optimized on Nvidia devices.☆90May 13, 2025Updated last year
- Flash Attention in ~100 lines of CUDA (forward pass only)☆12Jun 10, 2024Updated 2 years ago
- HunyuanDiT with TensorRT and libtorch☆18May 22, 2024Updated 2 years ago
- DeepStream Libraries offer CVCUDA, NvImageCodec, and PyNvVideoCodec modules as Python APIs for seamless integration into custom framewor…☆90Jul 14, 2026Updated 2 months ago
- MobileSAM のエンコーダー/デコーダーをONNXに変換し、推論するサンプル☆12Apr 11, 2024Updated 2 years ago
- Sample apps to demonstrate how to deploy models trained with TAO on DeepStream☆456Jul 15, 2026Updated 2 months ago
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆918Nov 20, 2023Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- C++ application to perform computer vision tasks using Nvidia Triton Server for model inference☆30Updated this week
- ☆74Sep 8, 2026Updated 2 weeks ago
- Llama3 Streaming Chat Sample☆22Apr 24, 2024Updated 2 years ago
- A shared library of on-demand DeepStream Pipeline Services for Python and C/C++☆346Mar 17, 2025Updated last year
- 大模型API性能指标比较 - 深入分析TTFT、TPS等关键指标☆20Sep 12, 2024Updated 2 years ago
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,717Updated this week
- ASR/NLP/TTS deep learning inference library for NVIDIA Jetson using PyTorch and TensorRT☆229Feb 9, 2024Updated 2 years ago