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

feat: add api.llama provider, llama-guard-4 model (#2058)

Browse source 
This PR adds a llama-stack inference provider for `api.llama.com`, as
well as adds entries for Llama-Guard-4 and updated Prompt-Guard models.
This commit is contained in:
Ashwin Bharambe 2025-04-29 10:07:41 -07:00 • committed by GitHub
parent 934446ddb4
commit 4d0bfbf984
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 1526 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

25
llama_stack/providers/remote/inference/llama_openai_compat/models.py Normal file
View file

@ -0,0 +1,25 @@
# 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_types import CoreModelId
from llama_stack.providers.utils.inference.model_registry import (
build_hf_repo_model_entry,
)
MODEL_ENTRIES = [
build_hf_repo_model_entry(
"Llama-3.3-70B-Instruct",
CoreModelId.llama3_3_70b_instruct.value,
),
build_hf_repo_model_entry(
"Llama-4-Scout-17B-16E-Instruct-FP8",
CoreModelId.llama4_scout_17b_16e_instruct.value,
),
build_hf_repo_model_entry(
"Llama-4-Maverick-17B-128E-Instruct-FP8",
CoreModelId.llama4_maverick_17b_128e_instruct.value,
),
]