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

88
llama_stack/templates/verification/run.yaml
View file

@ -502,104 +502,104 @@ models:
provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.1-8B-Instruct
model_id: sambanova/Meta-Llama-3.1-8B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.1-8B-Instruct
provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.1-8B-Instruct
provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.1-70B-Instruct
model_id: sambanova/Meta-Llama-3.1-405B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.1-70B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-70B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.1-70B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.1-405B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.1-405B-Instruct
provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.1-405B-Instruct
provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.2-1B-Instruct
model_id: sambanova/Meta-Llama-3.2-1B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.2-1B-Instruct
provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.2-1B-Instruct
provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.2-3B-Instruct
model_id: sambanova/Meta-Llama-3.2-3B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.2-3B-Instruct
provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.2-3B-Instruct
provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.3-70B-Instruct
model_id: sambanova/Meta-Llama-3.3-70B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.3-70B-Instruct
provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-3.3-70B-Instruct
provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: Llama-3.2-11B-Vision-Instruct
model_id: sambanova/Llama-3.2-11B-Vision-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Llama-3.2-11B-Vision-Instruct
provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Llama-3.2-11B-Vision-Instruct
provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: Llama-3.2-90B-Vision-Instruct
model_id: sambanova/Llama-3.2-90B-Vision-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Llama-3.2-90B-Vision-Instruct
provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Llama-3.2-90B-Vision-Instruct
provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-Guard-3-8B
model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-8B
provider_id: sambanova-openai-compat
provider_model_id: Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: Llama-4-Scout-17B-16E-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Llama-4-Scout-17B-16E-Instruct
provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: sambanova-openai-compat
provider_model_id: Llama-4-Scout-17B-16E-Instruct
provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
provider_id: sambanova-openai-compat
provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: sambanova-openai-compat
provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Meta-Llama-Guard-3-8B
provider_id: sambanova-openai-compat
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-8B
provider_id: sambanova-openai-compat
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: llama3.1-8b