From 7fe25927954d0ac00901091e3a01d06fc0ef09c9 Mon Sep 17 00:00:00 2001 From: snova-edwardm Date: Thu, 30 Jan 2025 09:24:46 -0800 Subject: [PATCH] SambaNova supports Llama 3.3 (#905) # What does this PR do? - Fix typo - Support Llama 3.3 70B ## Test Plan Run the following scripts and obtain the test results Script ``` pytest -s -v --providers inference=sambanova llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming --env SAMBANOVA_API_KEY={API_KEY} ``` Result ``` llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[-sambanova] PASSED =========================================== 1 passed, 1 warning in 1.26s ============================================ ``` Script ``` pytest -s -v --providers inference=sambanova llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming --env SAMBANOVA_API_KEY={API_KEY} ``` Result ``` llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[-sambanova] PASSED =========================================== 1 passed, 1 warning in 0.52s ============================================ ``` ## Sources Please link relevant resources if necessary. ## Before submitting - [N] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [Y] Ran pre-commit to handle lint / formatting issues. - [Y] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [Y] Updated relevant documentation. - [N] Wrote necessary unit or integration tests. --- docs/source/distributions/self_hosted_distro/sambanova.md | 2 +- .../providers/remote/inference/sambanova/sambanova.py | 4 ++++ llama_stack/templates/sambanova/run.yaml | 5 +++++ 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/docs/source/distributions/self_hosted_distro/sambanova.md b/docs/source/distributions/self_hosted_distro/sambanova.md index 199279990..6dbc0e94e 100644 --- a/docs/source/distributions/self_hosted_distro/sambanova.md +++ b/docs/source/distributions/self_hosted_distro/sambanova.md @@ -44,7 +44,7 @@ The following models are available by default: ### Prerequisite: API Keys -Make sure you have access to a SambaNova API Key. You can get one by visiting [SambaBova.ai](https://sambanova.ai/). +Make sure you have access to a SambaNova API Key. You can get one by visiting [SambaNova.ai](https://cloud.sambanova.ai/). ## Running Llama Stack with SambaNova diff --git a/llama_stack/providers/remote/inference/sambanova/sambanova.py b/llama_stack/providers/remote/inference/sambanova/sambanova.py index da446567a..b601d4b3f 100644 --- a/llama_stack/providers/remote/inference/sambanova/sambanova.py +++ b/llama_stack/providers/remote/inference/sambanova/sambanova.py @@ -57,6 +57,10 @@ MODEL_ALIASES = [ "Meta-Llama-3.2-3B-Instruct", CoreModelId.llama3_2_3b_instruct.value, ), + build_model_alias( + "Meta-Llama-3.3-70B-Instruct", + CoreModelId.llama3_3_70b_instruct.value, + ), build_model_alias( "Llama-3.2-11B-Vision-Instruct", CoreModelId.llama3_2_11b_vision_instruct.value, diff --git a/llama_stack/templates/sambanova/run.yaml b/llama_stack/templates/sambanova/run.yaml index c63b5d217..36f07dc73 100644 --- a/llama_stack/templates/sambanova/run.yaml +++ b/llama_stack/templates/sambanova/run.yaml @@ -116,6 +116,11 @@ models: provider_id: sambanova provider_model_id: Meta-Llama-3.2-3B-Instruct model_type: llm +- metadata: {} + model_id: meta-llama/Llama-3.3-70B-Instruct + provider_id: sambanova + provider_model_id: Meta-Llama-3.3-70B-Instruct + model_type: llm - metadata: {} model_id: meta-llama/Llama-3.2-11B-Vision-Instruct provider_id: sambanova