Comments (11)
关闭cuda算子加速可以有效解决该问题,可能是这方面的兼容性问题。
from rwkv-runner.
是什么显卡
from rwkv-runner.
3060 12G
from rwkv-runner.
3060 12G推荐用10G-7B这个设置
第一个回答出的慢是正常的,后续速度正常就没问题
from rwkv-runner.
后续的回答出的还是挺慢的。。。不过不是特别严重的问题。
from rwkv-runner.
策略需要优化一下 @josStorer 做个 12G 策略吧
from rwkv-runner.
@BlinkDL 目前10G显存已经足够使用完整的int8 7B模型了,所以没法再针对12G显存改进了,目前的12G策略是跑14B的
from rwkv-runner.
@doxtor6 加一下我QQ 1466587594 我给你远程看一下
from rwkv-runner.
好,已加。
from rwkv-runner.
v1.1.0已加入模型状态缓存提速
from rwkv-runner.
感受到了,效果还不错!不过我感觉我还是得换张显卡以获得更好的体验。
from rwkv-runner.
Related Issues (20)
- LoRa微调问题: 训练一段时间后 ,ubantu窗口和wsl窗口就关闭了 HOT 1
- 能不能加个深浅色模式自动跟随系统外观 HOT 2
- MacOS版本的停止按钮失效? HOT 1
- 切换.bin模型失败 HOT 6
- Trojans in Windows installer? (multiple detections from VirusTotal) HOT 1
- 我在本地配置了ollama,在聊天和续写时怎么调取? HOT 6
- 希望加入PISSA和LISA微调 HOT 2
- 【新人求助】如果想写小说,有什么模型推荐? HOT 1
- Win10 無法啟動 HOT 4
- CPU/CPU(rwkv.cpp) 模型切换问题 HOT 1
- 调用api接口感觉速度有点慢,是否和流式输出有关系,我看接口记录中流式输出参数是false,这个"stream": false, 参数在哪里可以设置呢? HOT 7
- 大佬,有兴趣加入Mirostat采样器吗? HOT 1
- 如何完全卸载呢? HOT 1
- 希望重新生成之前的对话时不会自动滚动到最后一段聊天
- JosStorer君,下载的东西都默认下载到C盘了。文件夹我是放到D盘的 HOT 1
- 模型运行成功,但发的所有消息都显示network error,控制台显示报错。 HOT 2
- 微调功能在上月新发布的 ubuntu 24.04 下失败
- 是否能够进行多batch的推理?
- install from source requirement.txt error on pkgutil
- 服务启动成功,但是访问报500 HOT 3
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 rwkv-runner.