phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-02 12:30:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(providers): sambanova updated to use LiteLLM openai-compat (#1596)

Browse source 
# What does this PR do?

switch sambanova inference adaptor to LiteLLM usage to simplify
integration and solve issues with current adaptor when streaming and
tool calling, models and templates updated

## Test Plan
pytest -s -v tests/integration/inference/test_text_inference.py
--stack-config=sambanova
--text-model=sambanova/Meta-Llama-3.3-70B-Instruct

pytest -s -v tests/integration/inference/test_vision_inference.py
--stack-config=sambanova
--vision-model=sambanova/Llama-3.2-11B-Vision-Instruct
This commit is contained in:
Jorge Piedrahita Ortiz 2025-05-06 18:50:22 -05:00 • committed by GitHub
parent dd49ef31f1
commit b2b00a216b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 529 additions and 404 deletions
Download patch file Download diff file Expand all files Collapse all files

32
llama_stack/providers/remote/inference/sambanova/models.py
View file

@ -11,43 +11,43 @@ from llama_stack.providers.utils.inference.model_registry import (
MODEL_ENTRIES = [
build_hf_repo_model_entry(
"Meta-Llama-3.1-8B-Instruct",
"sambanova/Meta-Llama-3.1-8B-Instruct",
CoreModelId.llama3_1_8b_instruct.value,
),
build_hf_repo_model_entry(
"Meta-Llama-3.1-70B-Instruct",
CoreModelId.llama3_1_70b_instruct.value,
),
build_hf_repo_model_entry(
"Meta-Llama-3.1-405B-Instruct",
"sambanova/Meta-Llama-3.1-405B-Instruct",
CoreModelId.llama3_1_405b_instruct.value,
),
build_hf_repo_model_entry(
"Meta-Llama-3.2-1B-Instruct",
"sambanova/Meta-Llama-3.2-1B-Instruct",
CoreModelId.llama3_2_1b_instruct.value,
),
build_hf_repo_model_entry(
"Meta-Llama-3.2-3B-Instruct",
"sambanova/Meta-Llama-3.2-3B-Instruct",
CoreModelId.llama3_2_3b_instruct.value,
),
build_hf_repo_model_entry(
"Meta-Llama-3.3-70B-Instruct",
"sambanova/Meta-Llama-3.3-70B-Instruct",
CoreModelId.llama3_3_70b_instruct.value,
),
build_hf_repo_model_entry(
"Llama-3.2-11B-Vision-Instruct",
"sambanova/Llama-3.2-11B-Vision-Instruct",
CoreModelId.llama3_2_11b_vision_instruct.value,
),
build_hf_repo_model_entry(
"Llama-3.2-90B-Vision-Instruct",
"sambanova/Llama-3.2-90B-Vision-Instruct",
CoreModelId.llama3_2_90b_vision_instruct.value,
),
build_hf_repo_model_entry(
"Meta-Llama-Guard-3-8B",
CoreModelId.llama_guard_3_8b.value,
),
build_hf_repo_model_entry(
"Llama-4-Scout-17B-16E-Instruct",
"sambanova/Llama-4-Scout-17B-16E-Instruct",
CoreModelId.llama4_scout_17b_16e_instruct.value,
),
build_hf_repo_model_entry(
"sambanova/Llama-4-Maverick-17B-128E-Instruct",
CoreModelId.llama4_maverick_17b_128e_instruct.value,
),
build_hf_repo_model_entry(
"sambanova/Meta-Llama-Guard-3-8B",
CoreModelId.llama_guard_3_8b.value,
),
]