phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

test: verification on provider's OAI endpoints (#1893)

Browse source 
# What does this PR do?


## Test Plan
export MODEL=accounts/fireworks/models/llama4-scout-instruct-basic;
LLAMA_STACK_CONFIG=verification pytest -s -v tests/integration/inference
--vision-model $MODEL --text-model $MODEL
This commit is contained in:
ehhuang 2025-04-07 23:06:28 -07:00 • committed by GitHub
parent 530d4bdfe1
commit 7b4eb0967e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
43 changed files with 1683 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/providers/remote/inference/together/models.py
View file

@ -64,4 +64,18 @@ MODEL_ENTRIES = [
"context_length": 32768,
},
),
build_hf_repo_model_entry(
"meta-llama/Llama-4-Scout-17B-16E-Instruct",
CoreModelId.llama4_scout_17b_16e_instruct.value,
additional_aliases=[
"together/meta-llama/Llama-4-Scout-17B-16E-Instruct",
],
),
build_hf_repo_model_entry(
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
CoreModelId.llama4_maverick_17b_128e_instruct.value,
additional_aliases=[
"together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
],
),
]

2
llama_stack/providers/remote/inference/together/together.py
View file

@ -118,7 +118,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
async def _stream_completion(self, request: CompletionRequest) -> AsyncGenerator:
params = await self._get_params(request)
client = await self._get_client()
client = self._get_client()
stream = await client.completions.create(**params)
async for chunk in process_completion_stream_response(stream):
yield chunk