Comments (3)
To disable GPU offloading (and you have a GPU detected) you must indeed set 0
in gpu_layers
. This is however poorly documented in the docs and likely need some expansion
from localai.
also this #1909 is related, I assume they have the same error
from localai.
@mudler it's also probably a good idea to pass out of VRAM memory
error instead of "error":{"code":500,"message":"rpc error: code = Unknown desc = unimplemented","type":""}}
from localai.
Related Issues (20)
- Exl2 models don't seem to be working with exllama2 HOT 1
- feat: [vLLM] Ability to use the tokenizer template
- feat: install flash-attn in the Docker image
- feat: llamafile backend HOT 1
- I would like to change the settings of llama-cpp in detail, but which file should I change? HOT 6
- Please support reranker API HOT 3
- docker download failure `4fadada67c94` - EOF HOT 3
- Building on macOS (Metal): "xcrun: error: unable to find utility "metal", not a developer tool or in PATH" HOT 1
- OpenVINO test on i3-N300 gives Method not implemented HOT 15
- Cannot fetch Huggingface gallery HOT 6
- limit models to api keys HOT 1
- After several exchanges, llama-cpp hangs up and no longer returns any response. HOT 7
- Very difficult to use, there are a lot of bugs HOT 2
- llama-cpp CPU 1500%๏ผVery slow...What to do? HOT 1
- tts coqui xtts_v2 not working without speaker_idx HOT 2
- ERROR [api builder 3/12] COPY .git . HOT 2
- LOCALAI_LOG_LEVEL seemingly does nothing HOT 4
- I would like the --tensor-parallel-size setting of the vllm backend to be added to yaml. HOT 1
- embeddings curl example on Mac "could not load model: rpc error" HOT 1
- lamma3 8B and 70B gguf support? Can support function calling? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from localai.