phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 07:12:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test fireworks

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-04-07 21:58:42 -07:00
parent c52ccc4bbd
commit 25374865a0
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