phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 20:44:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

init commit

Browse source
This commit is contained in:
Botao Chen 2025-03-11 20:55:24 -07:00
parent 27d5892dfa
commit 34d7fb649e
2 changed files with 26 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

25
llama_stack/templates/open-benchmark/open_benchmark.py
View file

@ -62,6 +62,16 @@ def get_inference_providers() -> Tuple[List[Provider], List[ModelInput]]:
],
GeminiConfig.sample_run_config(api_key="${env.GEMINI_API_KEY:}"),
),
(
"groq",
[],
GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:}"),
),
(
"together",
[],
TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:}"),
),
]
inference_providers = []
available_models = {}
@ -135,7 +145,20 @@ def get_distribution_template() -> DistributionTemplate:
),
]
default_models = get_model_registry(available_models)
default_models = get_model_registry(available_models) + [
ModelInput(
model_id="meta-llama/Llama-3.3-70B-Instruct",
provider_id="groq",
provider_model_id="groq/llama-3.3-70b-versatile",
model_type=ModelType.llm,
),
ModelInput(
model_id="meta-llama/Llama-3.1-405B-Instruct",
provider_id="together",
provider_model_id="meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
model_type=ModelType.llm,
),
]
default_datasets = [
DatasetInput(