[EMNLP Findings 2024] MobileQuant: Mobile-friendly Quantization for On-device Language Models
☆68Sep 22, 2024Updated last year
Alternatives and similar repositories for MobileQuant
Users that are interested in MobileQuant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- QAI AppBuilder is designed to help developers easily execute models on WoS and Linux platforms. It encapsulates the Qualcomm® AI Runtime …☆158Updated this week
- High-speed and easy-use LLM serving framework for local deployment☆153Aug 7, 2025Updated 9 months ago
- The repository supports TensorRT, QNN platform inference, 2D obstacle detection yolo series (yolov5, yolov8, yolo11, yolox), semantic seg…☆20May 6, 2025Updated last year
- This project is intended to build and deploy an SNPE model on Qualcomm Devices, which are having unsupported layers which are not part of…☆10Oct 4, 2021Updated 4 years ago
- Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK☆91Updated 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.
- Large Language Model Onnx Inference Framework☆35Nov 25, 2025Updated 5 months ago
- [MobiSys 2020] Fast and Scalable In-memory Deep Multitask Learning via Neural Weight Virtualization☆15Jun 9, 2020Updated 5 years ago
- Fast Multimodal LLM on Mobile Devices☆1,508Apr 30, 2026Updated 3 weeks ago
- [ICML 2022] ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks☆15May 18, 2022Updated 4 years ago
- Self-implemented NN operators for Qualcomm's Hexagon NPU☆68Sep 30, 2025Updated 7 months ago
- Tengine 管子是用来快速生产 demo 的辅助工具☆12Jul 15, 2021Updated 4 years ago
- FleetRec: Large-Scale Recommendation Inference on Hybrid GPU-FPGA Clusters☆17May 26, 2021Updated 4 years ago
- ☆14Feb 3, 2022Updated 4 years ago
- ☆18Dec 7, 2023Updated 2 years ago
- 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.
- JAX bindings for the flash-attention3 kernels☆22Jan 2, 2026Updated 4 months ago
- Tutorials of Extending and importing TVM with CMAKE Include dependency.☆16Oct 11, 2024Updated last year
- YOLOv5在高通AI Engine Direct环境下进行QNN量化，CPU推理的项目☆17Sep 10, 2024Updated last year
- 基于 CUDA Driver API 的 cuda 运行时环境☆16Jul 30, 2025Updated 9 months ago
- MPI Code Generation through Domain-Specific Language Models☆15Nov 19, 2024Updated last year
- ☆75Apr 13, 2026Updated last month
- Model Quantization Benchmark☆19Apr 17, 2026Updated last month
- [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…☆40Mar 11, 2024Updated 2 years ago
- Run Chinese MobileBert model on SNPE.☆15May 19, 2023Updated 3 years ago
- 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.
- ☆31Aug 11, 2024Updated last year
- Example of opencl on android. Edit from this bolg: http://developer.sonymobile.com/2013/10/29/boost-the-performance-of-your-android-app-w…☆10Mar 31, 2014Updated 12 years ago
- ☆15Sep 24, 2023Updated 2 years ago
- Anatomy of a powerhouse: SystemVerilog TPU based on Google TPU v1☆22Nov 9, 2025Updated 6 months ago
- On-device AI across mobile, embedded and edge for PyTorch☆4,622Updated this week
- What Would Portland Do? Generative agent experience☆13Mar 13, 2024Updated 2 years ago
- This is the repository containing the implementation of sparse dense matrix multiplication for the matrix dimension of 560 x 560.☆10Jul 7, 2021Updated 4 years ago
- Petri Net Simulator program☆10Nov 27, 2017Updated 8 years ago
- ☆49Apr 29, 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.
- A tool to transform Android Cuttlefish images into QEMU disk images☆17Jul 12, 2024Updated last year
- ☆82Jul 21, 2022Updated 3 years ago
- ☆21Apr 3, 2025Updated last year
- Simodense: a RISC-V softcore for custom SIMD instructions☆17Feb 16, 2026Updated 3 months ago
- WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models☆23Jul 10, 2025Updated 10 months ago
- Guide to build FFmpeg from source with Netflix's libvmaf on Ubuntu 18.04☆11Oct 12, 2020Updated 5 years ago
- ☆18Apr 25, 2025Updated last year