Comments (4)
@netandreus this seems to likely happen when the prompt exhausts the context size - can you check if that's causing issues in your case by bumping the context size?
In any case sounds reasonable to bail out early instead of trying to free space in the KV cache. this seem also related to #2258 - can you also try by setting batch
to 1
in the model configuration and see if keeps happening?
parameters:
batch: 1
from localai.
related to #2258
from localai.
Thank you for assistance, I will check.
from localai.
It seems that this error also happens if we enable parallel llama.cpp processing. For an example, setting the context size to 8192 and the number of parallel processes to 20, the token stream generation always stops at around 410 characters, which is roughly equal to 8192 divided by 20.
So, instead of each process allocating 8192 context window size, as specified in the .env/yaml file, the backend takes this value and splits it between all the processes.
Is this a bug or expected behaviour? If it's expected it might not be a bad idea to clarify this behaviour in the documentation.
from localai.
Related Issues (20)
- [BUG] setuptools 70.0.0 breaks PyTorch 2.1
- Feature Discussion: Role-Based Auth HOT 2
- The API v1/images/generations do not apply the size
- Please integrate chatTTS HOT 1
- Error grabbing logs: invalid character '\x00' looking for beginning of value
- Distributed Llama.cpp Inferencing option `llamacpp-worker` not working HOT 2
- animagine-xl not working on latest-cpu
- Site missing "WEBUI" info
- Chat WebUI stops updating HOT 1
- Rerank API not accessible: {"error":{"code":500,"message":"grpc service not ready","type":""}} HOT 1
- Parler-tts doesn't work when installed from gallery, documentation unhelpful
- coqui tts: change to better maintained fork HOT 2
- Transformers backend supports mps
- API appears to hang forever if a response is interrupted HOT 1
- support models from OCI registry
- Timeout
- add zsh/bash autocompletion to local-ai CLI
- Feature request: Request the ability to upload a private SSL certificate provided by a secure solution for downloading models HOT 1
- Feature request: Request the ability to upload a private SSL certificate provided by a secure solution for downloading models HOT 2
- Quickstart not working HOT 7
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 localai.