mperf是一个面向移动/嵌入式平台的算子性能调优工具箱
☆197Aug 17, 2023Updated 3 years ago
Alternatives and similar repositories for mperf
Users that are interested in mperf are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆256Sep 15, 2023Updated 3 years ago
- MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器☆483Oct 23, 2024Updated last year
- row-major matmul optimization☆755May 14, 2026Updated 4 months ago
- MegEngine到其他框架的转换器☆71Apr 27, 2023Updated 3 years ago
- This is a demo how to write a high performance convolution run on apple silicon☆56Feb 8, 2022Updated 4 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.
- Yinghan's Code Sample☆367Jul 25, 2022Updated 4 years ago
- TVMScript kernel for deformable attention☆25Dec 15, 2021Updated 4 years ago
- ☆99May 20, 2026Updated 3 months ago
- This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several…☆1,360Jul 29, 2023Updated 3 years ago
- a lightweight LLM model inference framework☆752Apr 7, 2024Updated 2 years ago
- ☆15Apr 29, 2024Updated 2 years ago
- A primitive library for neural network☆1,367Nov 24, 2024Updated last year
- A profiler to disclose and quantify hardware features on GPUs.☆175May 15, 2022Updated 4 years ago
- Common libraries for PPL projects☆31Mar 10, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- symmetric int8 gemm☆67Jun 7, 2020Updated 6 years ago
- ☆2,040Jul 29, 2023Updated 3 years ago
- stable diffusion using mnn☆68Sep 28, 2023Updated 2 years ago
- A simple high performance CUDA GEMM implementation.☆440Jan 4, 2024Updated 2 years ago
- an example of segment-anything infer by ncnn☆123May 5, 2023Updated 3 years ago
- GPTQ inference TVM kernel☆41Apr 25, 2024Updated 2 years ago
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,822Mar 28, 2024Updated 2 years ago
- Tutorials for writing high-performance GPU operators in AI frameworks.☆135Aug 12, 2023Updated 3 years ago
- A model compilation solution for various hardware☆475Aug 20, 2025Updated last year
- 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.
- LLaMa/RWKV onnx models, quantization and testcase☆367Jul 6, 2023Updated 3 years ago
- ppl.cv is a high-performance image processing library of openPPL supporting various platforms.☆517Oct 30, 2024Updated last year
- CUDA Templates for Linear Algebra Subroutines☆102Apr 25, 2024Updated 2 years ago
- MegEngine implementation of Diffusion Models.☆19Aug 8, 2022Updated 4 years ago
- ☆139Jul 31, 2026Updated last month
- SAM and lama inpaint，包 含QT的GUI交互界面，实现了交互式可实时显示结果的画点、画框进行SAM，然后通过进行Inpaint，具体操作看readme里的视频。☆54Jan 30, 2024Updated 2 years ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆479Mar 15, 2024Updated 2 years ago
- An easy way to run, test, benchmark and tune OpenCL kernel files☆24Aug 25, 2023Updated 3 years ago
- ☆126Dec 15, 2023Updated 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.
- study of cutlass☆22Nov 10, 2024Updated last year
- AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。☆746Sep 23, 2022Updated 3 years ago
- ☆140Apr 23, 2024Updated 2 years ago
- ☆75Sep 8, 2022Updated 4 years ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated 2 months ago
- A lightweight, single-header C++11 Jinja2 template engine for LLM chat templates.☆20Mar 4, 2026Updated 6 months ago
- segment-anything based mnn☆37Dec 13, 2023Updated 2 years ago