phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-27 06:28:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(starter)!: simplify starter distro; litellm model registry changes (#2916)

Browse source
This commit is contained in:
Ashwin Bharambe 2025-07-25 15:02:04 -07:00 • committed by GitHub
parent 3344d8a9e5
commit 9583f468f8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
64 changed files with 2027 additions and 4092 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/groq/config.py
View file

@ -32,7 +32,7 @@ class GroqConfig(BaseModel):
)
@classmethod
def sample_run_config(cls, api_key: str = "${env.GROQ_API_KEY}", **kwargs) -> dict[str, Any]:
def sample_run_config(cls, api_key: str = "${env.GROQ_API_KEY:=}", **kwargs) -> dict[str, Any]:
return {
"url": "https://api.groq.com",
"api_key": api_key,

3
llama_stack/providers/remote/inference/groq/groq.py
View file

@ -34,6 +34,7 @@ class GroqInferenceAdapter(LiteLLMOpenAIMixin):
LiteLLMOpenAIMixin.__init__(
self,
model_entries=MODEL_ENTRIES,
litellm_provider_name="groq",
api_key_from_config=config.api_key,
provider_data_api_key_field="groq_api_key",
)
@ -96,7 +97,7 @@ class GroqInferenceAdapter(LiteLLMOpenAIMixin):
tool_choice = "required"
params = await prepare_openai_completion_params(
model=model_obj.provider_resource_id.replace("groq/", ""),
model=model_obj.provider_resource_id,
messages=messages,
frequency_penalty=frequency_penalty,
function_call=function_call,

22
llama_stack/providers/remote/inference/groq/models.py
View file

@ -14,19 +14,19 @@ SAFETY_MODELS_ENTRIES = []
MODEL_ENTRIES = [
build_hf_repo_model_entry(
"groq/llama3-8b-8192",
"llama3-8b-8192",
CoreModelId.llama3_1_8b_instruct.value,
),
build_model_entry(
"groq/llama-3.1-8b-instant",
"llama-3.1-8b-instant",
CoreModelId.llama3_1_8b_instruct.value,
),
build_hf_repo_model_entry(
"groq/llama3-70b-8192",
"llama3-70b-8192",
CoreModelId.llama3_70b_instruct.value,
),
build_hf_repo_model_entry(
"groq/llama-3.3-70b-versatile",
"llama-3.3-70b-versatile",
CoreModelId.llama3_3_70b_instruct.value,
),
# Groq only contains a preview version for llama-3.2-3b
@ -34,23 +34,15 @@ MODEL_ENTRIES = [
# to pass the test fixture
# TODO(aidand): Replace this with a stable model once Groq supports it
build_hf_repo_model_entry(
"groq/llama-3.2-3b-preview",
"llama-3.2-3b-preview",
CoreModelId.llama3_2_3b_instruct.value,
),
build_hf_repo_model_entry(
"groq/llama-4-scout-17b-16e-instruct",
"meta-llama/llama-4-scout-17b-16e-instruct",
CoreModelId.llama4_scout_17b_16e_instruct.value,
),
build_hf_repo_model_entry(
"groq/meta-llama/llama-4-scout-17b-16e-instruct",
CoreModelId.llama4_scout_17b_16e_instruct.value,
),
build_hf_repo_model_entry(
"groq/llama-4-maverick-17b-128e-instruct",
CoreModelId.llama4_maverick_17b_128e_instruct.value,
),
build_hf_repo_model_entry(
"groq/meta-llama/llama-4-maverick-17b-128e-instruct",
"meta-llama/llama-4-maverick-17b-128e-instruct",
CoreModelId.llama4_maverick_17b_128e_instruct.value,
),
] + SAFETY_MODELS_ENTRIES