llama-stack

llama-stack copied to clipboard

llama cli does not work on mac Sequoia

13

Hi, I have installed llama cli, but getting below error for any command. I installed it with `pip3 install llama-stack`. This prevents further usage of llama-stack, could you please guide...

kavukcutolga

Add timeout to requests calls

1

Many developers will be surprised to learn that `requests` library calls do not include timeouts by default. This means that an attempted request could hang indefinitely if no connection is...

pixeeai

Ollama build docker image still looks for GPU support on run

1

If I run build for ollama with docker, after configuring and running the docker image, the docker image still looks for GPU support and fails. Steps to recreate. llama stack...

clearstorm-tech

In the previous design, the server endpoint at the top-most level extracted the headers from the request and set provider data (e.g., private keys) that the implementations could retrieve using...

ashwinb

VLLM / OpenAI Compatible endpoint support

1

The current implementation of local means no sharding/tensor parallelism, etc, and refuses to work on my dual 4090 setup. How do I enable multi gpu, or how do I enable...

matbeedotcom

fix broken bedrock inference provider

2

Support for Bedrock inference providers has been applied with the following merges: https://github.com/meta-llama/llama-stack/commit/95abbf576b4b078e72b779f534cbaf696e30ecab However, it was overwritten in the next merge. https://github.com/meta-llama/llama-stack/commit/56aed59eb4c9915676c6fc7aac009dad97e7ead2 As a result, Bedrock is not displayed as...

moritalous

In this file image is not show https://github.com/meta-llama/llama-stack/blob/main/docs/cli_reference.md 

scenaristeur

Add Runpod Provider

6

**Why this PR** We want to add [Runpod](https://www.runpod.io/) as remote inference provider for Llama-stack. [Runpod](https://www.runpod.io/) endpoints are OpenAI Compatible, hence it's recommended to use it with Runpod model serving endpoints....

pandyamarut

Help Needed for understanding

1

Can someone help me understand how the is the context being tracked for agent turn create API, or for the inference chat completion API? I want to understand how its...

cheesecake100201

run local ollama failed.

1

Run client failed by ``` $ python -m llama_stack.apis.inference.client localhost 11434 User>hello world, write me a 2 sentence poem about the moon Error: HTTP 404 404 page not found ```...

alexhegit