mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-30 16:53:12 +00:00
8a1c0a1008
This doesn't get Groq to 100% on the OpenAI API verification tests, but it does get it to 88.2% when Llama Stack is in the middle, compared to the 61.8% results for using an OpenAI client against Groq directly. The groq provider doesn't use litellm under the covers in its openai_chat_completion endpoint, and instead directly uses an AsyncOpenAI client with some special handling to improve conformance of responses for response_format usage and tool calling. Signed-off-by: Ben Browning <bbrownin@redhat.com>
54 lines
1.8 KiB
Python
54 lines
1.8 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from llama_stack.models.llama.sku_list import CoreModelId
|
|
from llama_stack.providers.utils.inference.model_registry import (
|
|
build_hf_repo_model_entry,
|
|
build_model_entry,
|
|
)
|
|
|
|
MODEL_ENTRIES = [
|
|
build_hf_repo_model_entry(
|
|
"groq/llama3-8b-8192",
|
|
CoreModelId.llama3_1_8b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"groq/llama-3.1-8b-instant",
|
|
CoreModelId.llama3_1_8b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"groq/llama3-70b-8192",
|
|
CoreModelId.llama3_70b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"groq/llama-3.3-70b-versatile",
|
|
CoreModelId.llama3_3_70b_instruct.value,
|
|
),
|
|
# Groq only contains a preview version for llama-3.2-3b
|
|
# Preview models aren't recommended for production use, but we include this one
|
|
# 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",
|
|
CoreModelId.llama3_2_3b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"groq/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",
|
|
CoreModelId.llama4_maverick_17b_128e_instruct.value,
|
|
),
|
|
]
|