llama-stack

llama-stack copied to clipboard

Adds support for inference with Snowflake's Cortex endpoint. See docs for more background on Cortex:https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-llm-rest-api Testing - built a new stack from scratch using remote::snowflake for the Inference API -...

sfc-gh-alherrera

Model ids that contains a colon throws error when trying to install on Windows

1

### System Info Windows 11 Python 3.12.7 (and 3.12.5 apparently depending on running py --version or python --version from PowerShell) ### Information - [X] The official example scripts - [...

Sandstedt

feat: azure ai inference support

4

# What does this PR do? This PR introduces support for Azure AI model inference API with the id `remote::azure-ai-inference`. Closes # (issue) ## Feature/Issue validation/testing/test plan Please describe the...

santiagxf

Enable distributuion/ollama for rocm

3

### 🚀 The feature, motivation and pitch Ollama has the docker image [ollama/ollama:rocm](https://hub.docker.com/layers/ollama/ollama/rocm/images/sha256-2368286e0fca3b4f56e017a9aa4809408d8a8c6596e3cbd34b0837f5dafd7b6b?context=explore) support AMD ROCm . I wish distributuion/ollama could support AMD ROCm as https://github.com/meta-llama/llama-stack/tree/main/distributions/ollama/gpu for NVIDIA GPU. I...

alexhegit

Add Runpod Provider + Distribution

4

Add Runpod as a inference provider for openAI compatible managed endpoints. Testing - Configured llama stack from scratch, set `remote::runpod` as a inference provider. - Added Runpod Endpoint URL and...

pandyamarut

# What does this PR do? Migrates all the existing tools in agent_instance to tool_runtime and adds an easy way to author new tools ## Test Plan TODO.

dineshyv

## What does this PR do? In this PR, we refactor the meta reference inference logic to support - load the model during registering model instead of during spinning up...

SLR722

This PR adds a new Tools api and does all the plumbing needed to implement the tools api in distribution and changes needed to route the tool runtime calls to...

dineshyv

# What does this PR do? Adds a very simple tool runtime which calls any function defined in builtins.py ## Test Plan ``` curl -X POST "http://localhost:5000/alpha/tools/register" \ -H "Content-Type:...

dineshyv

Agent's tests are failing with ScopeMismatch

3

### System Info WIndows/WSL Ubuntu 22.xx ### Information - [ ] The official example scripts - [ ] My own modified scripts ### 🐛 Describe the bug Trying to run...

apryiomka