yijinsheng

online模型运行时间长了之后响应速度变慢

3

1. 运行环境： 操作系统：linux python：3.8 torch:2.0.0 modelscope:1.9.3 gpu:p100, 显卡驱动535， cuda:11.7 2.执行代码 ``` from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks from modelscope.utils.logger import get_logger import tracemalloc import logging tracemalloc.start() logger =...

能否支持lora，controlnet这些？

4

如题

build ffmpeg error on macos

2

i want to compile the ffmpeg on my macos, I use the command > mvn install --projects .,ffmpeg -Djavacpp.platform.extension=-gpl and I get the error message ` ld: warning: -single_module is...

how to free my cuda memory using nvcomp

2

I have follow the example [nvcompLZ4Example](https://github.com/bytedeco/javacpp-presets/blob/master/cuda/samples/nvcompLZ4Example.java) to compress my yuv data using 3090TI. but I have 2 questions about this. 1. when I go throuth all the code , there...