Comments (6)
I need some more information:
- What operating system do you have?
- What model of GPU are you currently using?
- What device is being used in GPT4All 2.6.1 and GPT4All 2.7.3? It will tell you this next to the token count. If one is using the GPU and the other is not (possibly due to OOM), that would explain the speed difference.
There were significant changes to the GPU backend in v2.6.2.
from gpt4all.
Windows 10 in a VM.
I'm using NVIDIA GT1030.
I never noticed the device beside the token count before but in both cases it only says CPU. Once again, I got 3.8 t/s on 2.6.1 and 1.6 on 2.7.3. Exact same setup.
So my GPU was never utilized, interesting.
from gpt4all.
Thanks for the reply. To help narrow down the issue further, could you try a few versions between 2.6.1 and 2.7.3 to find which specific version caused the slowdown? Here are links to the versions in between:
- https://github.com/nomic-ai/gpt4all/releases/tag/v2.6.2
- https://github.com/nomic-ai/gpt4all/releases/tag/v2.7.0
- https://github.com/nomic-ai/gpt4all/releases/tag/v2.7.1
- https://github.com/nomic-ai/gpt4all/releases/tag/v2.7.2
from gpt4all.
Good catch! 2.6.2 appears to be the culprit. 3.2 t/s on 2.6.1, 1.1 t/s on 2.6.2. The output was worse too but that's just my subjective opinion.
from gpt4all.
Windows 10 in a VM.
By the way - GPT4All will likely not be able to see your GPU inside of a virtual machine, unless you are a real power user doing PCIe passthrough. It most likely does not appear as an option under Settings > Application > Device.
from gpt4all.
Windows 10 in a VM.
By the way - GPT4All will likely not be able to see your GPU inside of a virtual machine, unless you are a real power user doing PCIe passthrough. It most likely does not appear as an option under Settings > Application > Device.
Hey, have you figured out the cause of the regression yet?
My Windows 10 box is not ready, but when I tested it on Windows 10 on the same hardware (not a VM) I got 4.9 t/s, not a huge improvement. However, this was while I was using the onboard GPU so no idea what a GT1030 would do.
from gpt4all.
Related Issues (20)
- [Docs] Document a few specific pain-points in an FAQ or troubleshooting page HOT 1
- [Crash] Assertion `isModelLoaded()` fails in ChatLLM::generateName when switching chats while model is generating
- Explore Models search shows HF results for architectures that are not whitelisted in the backend
- [Feature] Add a file similar to .gitignore for LocalDocs
- The application still gets deleted in Windows10 HOT 7
- Clones are showing up in the installed models view
- Provide new chunking strategies in localdocs HOT 2
- Feature request: Support dynamic changing of language at runtime HOT 6
- chrash while talk with docs HOT 4
- [Keyboard Accessibility] Make GPT4All keyboard accessible (fully navigable and functional with keyboard only) HOT 1
- [Screenreader Accessibility] Make GPT4All screenreader accessible HOT 3
- [Color/Contrast/Visibility Accessibility] Make GPT4All color/contrast/visibility accessible HOT 4
- [Feature] Option to "Lock" a localDocs collection to prevent reindex. HOT 3
- Indexing gets stuck if filenames have square brackets HOT 2
- [Feature] Upgrade llama.cpp to support Phi-3-mini-128k-instruct and IBM Granite HOT 2
- [Feature] Export a profile of model setting
- adding tools HOT 1
- [Feature] Search grounding for questions in chat (Duckduckgo, Google, Bing, and APIs)
- [Feature] doc indexing and embedding
- Crash on launch HOT 9
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 gpt4all.