-
**LocalAI version:**
localai/localai:latest-aio-cpu
**Environment, CPU architecture, OS, and Version:**
cpu
**Describe the bug**
api_1 | 8:39AM INF [llama-cpp] Fails: could not lo…
-
I migrated my application from jersey 2.x to 3.x along with spring boot. Previously when I throw any `RuntimeException`, the errors will be mapped to **MappableException class** and processed. But aft…
-
### What happened?
I'm using the `openai` library to interact with `llama-server` docker image on an A6000:
`docker run -p 8080:8080 --name llama-server -v ~/gguf_models:/models --gpus all ghcr.io…
-
### Motivation
CUDA_VISIBLE_DEVICES=3,4 lmdeploy serve api_server /home/ma/work/modelscope/glm-4-9b-chat-GPTQ-Int4 --backend turbomind --model-format gptq --server-port 11231 --tp 2 --session-len 165…
-
### What happened?
For Manual Metric Collection and Training with Entrypoint, all models produced appears to have an extracted folder and a zipped folder with the exception of LogisticRegression.
##…
-
Better to change model's import style from, say `import CollectionGroup from "./CollectionGroup";` to `import { CollectionGroup } from "@server/models";` everywhere. Reason being that in the former, t…
-
This [paper](https://aclanthology.org/2020.emnlp-demos.15.pdf) about LIT mentions that a model on a remote server can be analyzed using LIT but I am struggling to understand exactly how to do that. Ca…
-
We want to implement batch processing for the image classifier and thus increase throughput.
1. Decouple the web server from the AI model evaluator, and make the web server scale with more requests…
-
### What is the issue?
When I try `ollama run llama3.1:70b`, occur error `Error: llama runner process has terminated: error loading model: unable to allocate backend buffer`
```
C:\Users\sol>olla…
-
In Marquez, we're planning to use the models defined in pkg `io.openlineage.server.*` to collect OpenLineage events:
```java
@POST
@Consumes(APPLICATION_JSON)
@Path("/lineage")
public R…