mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
967cff4533
# What does this PR do? Create a distribution template using Groq as inference provider. Link to issue: https://github.com/meta-llama/llama-stack/issues/958 ## Test Plan Run `python llama_stack/scripts/distro_codegen.py` to generate run.yaml and build.yaml Test the newly created template by running `llama stack build --template <template-name>` `llama stack run <template-name>`
29 lines
622 B
YAML
29 lines
622 B
YAML
version: '2'
|
|
distribution_spec:
|
|
description: Use Groq for running LLM inference
|
|
providers:
|
|
inference:
|
|
- remote::groq
|
|
vector_io:
|
|
- inline::faiss
|
|
safety:
|
|
- inline::llama-guard
|
|
agents:
|
|
- inline::meta-reference
|
|
telemetry:
|
|
- inline::meta-reference
|
|
eval:
|
|
- inline::meta-reference
|
|
datasetio:
|
|
- remote::huggingface
|
|
- inline::localfs
|
|
scoring:
|
|
- inline::basic
|
|
- inline::llm-as-judge
|
|
- inline::braintrust
|
|
tool_runtime:
|
|
- remote::brave-search
|
|
- remote::tavily-search
|
|
- inline::code-interpreter
|
|
- inline::rag-runtime
|
|
image_type: conda
|