Comments (1)
在3090上用cuda跑,在agent的run函数中添加了打印结果和显示时间的代码
generate prompt and call llm
prompt = self.prompt_generator.generate(llm_result, exec_result) start = time.time() llm_result = self.llm.generate(prompt) end = time.time() print(f"===llm_result: {llm_result}, time: {end-start}")
结果发现生成下面几个字符都要20s时间。 ===llm_result: 明天杭州的天气预计是晴天,需要注意防晒哦。, time: 20.340392589569092
性能这么慢不正常吧,完全没法使用,请问可能是什么原因导致。 另外flash_attn安装成功,但是rms_norm 和rotary两个库没有编成功,编译的时候一直卡住。
这个推理时间确实有点异常,可能是环境问题,你这边直接使用modelscope对应模型的pipeline推理需要多久呢,比如这个:
https://modelscope.cn/models/damo/ModelScope-Agent-7B/summary
from modelscope-agent.
Related Issues (20)
- 调用远程文字转图片报错 HOT 1
- 使用vllm启动ModelScope-Agent-14B 无法停止 HOT 2
- demo里面的用例有些过时了,更新下用例吧 HOT 2
- gradio 导入失败啊 HOT 2
- modescope agent 训练Qwen 为什么采用<|user|>而不是<|im_start|> HOT 2
- 请问什么时候添加azure openai的支持呢 HOT 2
- win11操作系统运行apps里面的agentfabric应用,当配置(Configure)时勾选“内置能力”:Code Interpreter,点击更新配置会报错 HOT 1
- 模型下载出错 HOT 3
- 添加额外工具列表报错 HOT 2
- Bug解答:点击构建按钮报错? HOT 4
- openapi schema解析不完全 HOT 3
- ImportError: cannot import name 'print_model_info' from 'swift.utils' HOT 1
- 预训练代码报错 HOT 3
- name 'history' is not defined in modelscope-agent/apps/msgpt/predict.py file HOT 5
- 预训练显存不够 HOT 1
- 急急急!使用本地向量库时,报一个告警,且最后调用agent输出时候出错了,没有结果 HOT 2
- 对于论文中提到的数据集生成方法,可以发下代码参考一下吗? HOT 2
- 关于AgentFabric和ModelScope的Bug HOT 6
- 本地部署apps/msgpt出错,可以正常请求,但回答是空白 HOT 12
- 目前ModelScope-Agent支持的模型有哪些? HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from modelscope-agent.