phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(providers): Groq now uses LiteLLM openai-compat (#1303)

Browse source 
Groq has never supported raw completions anyhow. So this makes it easier
to switch it to LiteLLM. All our test suite passes.

I also updated all the openai-compat providers so they work with api
keys passed from headers. `provider_data`

## Test Plan

```bash
LLAMA_STACK_CONFIG=groq \
   pytest -s -v tests/client-sdk/inference/test_text_inference.py \
   --inference-model=groq/llama-3.3-70b-versatile --vision-inference-model=""
```

Also tested (openai, anthropic, gemini) providers. No regressions.
This commit is contained in:
Ashwin Bharambe 2025-02-27 13:16:50 -08:00 • committed by GitHub
parent 564f0e5f93
commit 928a39d17b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 165 additions and 1004 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/client-sdk/conftest.py
View file

@ -117,7 +117,9 @@ def client_with_models(llama_stack_client, text_model_id, vision_model_id, embed
assert len(providers) > 0, "No inference providers found"
inference_providers = [p.provider_id for p in providers if p.provider_type != "inline::sentence-transformers"]
model_ids = [m.identifier for m in client.models.list()]
model_ids = set(m.identifier for m in client.models.list())
model_ids.update(m.provider_resource_id for m in client.models.list())
if text_model_id and text_model_id not in model_ids:
client.models.register(model_id=text_model_id, provider_id=inference_providers[0])
if vision_model_id and vision_model_id not in model_ids:

2
tests/client-sdk/inference/test_text_inference.py
View file

@ -18,7 +18,7 @@ def skip_if_model_doesnt_support_completion(client_with_models, model_id):
provider_id = models[model_id].provider_id
providers = {p.provider_id: p for p in client_with_models.providers.list()}
provider = providers[provider_id]
if provider.provider_type in ("remote::openai", "remote::anthropic", "remote::gemini"):
if provider.provider_type in ("remote::openai", "remote::anthropic", "remote::gemini", "remote::groq"):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support completion")