面向移动设备的实时人像分割
int8-inference 开源项目推荐(18 个)
int8-inference 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 全部 18
GitHub 共 18 个仓库,已全部展示BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).
Generate a quantization parameter file for ncnn framework int8 inference
Quantization Aware Training
将端上模型部署过程中,常见的问题以及解决办法记录并汇总,希望能给其他人带来一点帮助。
TensorRT Int8 Python version sample. TensorRT Int8 Python 实现例子。TensorRT Int8 Pythonの例です
GPT-J 6B inference on TensorRT with INT-8 precision
该项目在 GitHub 上没有填写描述
VB.NET api wrapper for llm-inference chatllm.cpp
C# api wrapper for llm-inference chatllm.cpp
Generating tensorrt model using onnx
Compressed CNNs for airplane classification in satellite images (APoZ-based parameter pruning, INT8 weight quantization)
gemma-2-2b-it int8 cpu inference in one file of pure C#
g023's TurboXInf 🚀: 2x+ faster inference for Qwen3-1.77B or Qwen3.5-2B on RTX 3060! Custom Triton INT8 GEMV kernels halve memory traffic by fusing dequantization, paired with torch.compile. Hits 113 tok/s (vs 56.4 baseline) with no quality loss with INT8 even better results for INT4. MIT License.
The project combines VHDL RTL design, INT8 AI arithmetic, computer-vision preprocessing, motor control, safety mechanisms, and ROS 2 integration in one modular platform. Its purpose is to provide a practical learning and development environment for building hardware-accelerated Physical AI systems.
Qwen3.6-first tiered-memory CPU inference for sparse expert models.
it has support for openvino converted model of yolov7-int.xml ,yolov7x,
Python wrapper for the libann neural network library with a Keras-like API.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 18 个项目;原始页面见 https://github.com/topics/int8-inference。
- 该话题在 GitHub 上共有 18 个仓库, 本站收录的是其中最热门的 18 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 18 个项目累计 1932 Star,覆盖 6 种主要语言,数据更新于 2026-11-10。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。