From bed93ec5528c5f1d4ef8fb9f3bd63cf386c39ae2 Mon Sep 17 00:00:00 2001 From: jhpiedrahitao Date: Wed, 12 Mar 2025 15:29:10 -0500 Subject: [PATCH] update dev template --- llama_stack/templates/dev/build.yaml | 1 + llama_stack/templates/dev/dev.py | 7 ++ llama_stack/templates/dev/run.yaml | 95 ++++++++++++++++++++++++++++ 3 files changed, 103 insertions(+) diff --git a/llama_stack/templates/dev/build.yaml b/llama_stack/templates/dev/build.yaml index 726ebccca..f80892135 100644 --- a/llama_stack/templates/dev/build.yaml +++ b/llama_stack/templates/dev/build.yaml @@ -8,6 +8,7 @@ distribution_spec: - remote::anthropic - remote::gemini - remote::groq + - remote::sambanova - inline::sentence-transformers vector_io: - inline::sqlite-vec diff --git a/llama_stack/templates/dev/dev.py b/llama_stack/templates/dev/dev.py index 1aee1bb22..d7cb8c2d7 100644 --- a/llama_stack/templates/dev/dev.py +++ b/llama_stack/templates/dev/dev.py @@ -27,6 +27,8 @@ from llama_stack.providers.remote.inference.groq.config import GroqConfig from llama_stack.providers.remote.inference.groq.models import MODEL_ENTRIES as GROQ_MODEL_ENTRIES from llama_stack.providers.remote.inference.openai.config import OpenAIConfig from llama_stack.providers.remote.inference.openai.models import MODEL_ENTRIES as OPENAI_MODEL_ENTRIES +from llama_stack.providers.remote.inference.sambanova.config import SambaNovaImplConfig +from llama_stack.providers.remote.inference.sambanova.models import MODEL_ENTRIES as SAMBANOVA_MODEL_ENTRIES from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVectorIOConfig from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry @@ -60,6 +62,11 @@ def get_inference_providers() -> Tuple[List[Provider], List[ModelInput]]: GROQ_MODEL_ENTRIES, GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:}"), ), + ( + "sambanova", + SAMBANOVA_MODEL_ENTRIES, + SambaNovaImplConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:}"), + ), ] inference_providers = [] available_models = {} diff --git a/llama_stack/templates/dev/run.yaml b/llama_stack/templates/dev/run.yaml index f908af8c3..29c381f4d 100644 --- a/llama_stack/templates/dev/run.yaml +++ b/llama_stack/templates/dev/run.yaml @@ -34,6 +34,11 @@ providers: config: url: https://api.groq.com api_key: ${env.GROQ_API_KEY:} + - provider_id: sambanova + provider_type: remote::sambanova + config: + url: https://api.sambanova.ai/v1 + api_key: ${env.SAMBANOVA_API_KEY} - provider_id: sentence-transformers provider_type: inline::sentence-transformers config: {} @@ -343,6 +348,96 @@ models: provider_id: groq provider_model_id: groq/llama-3.2-3b-preview model_type: llm +- metadata: {} + model_id: sambanova/Meta-Llama-3.1-8B-Instruct + provider_id: sambanova + 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 + provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct + model_type: llm +- metadata: {} + model_id: sambanova/Meta-Llama-3.1-70B-Instruct + provider_id: sambanova + provider_model_id: sambanova/Meta-Llama-3.1-70B-Instruct + model_type: llm +- metadata: {} + model_id: meta-llama/Llama-3.1-70B-Instruct + provider_id: sambanova + provider_model_id: sambanova/Meta-Llama-3.1-70B-Instruct + model_type: llm +- metadata: {} + model_id: sambanova/Meta-Llama-3.1-405B-Instruct + provider_id: sambanova + 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 + provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct + model_type: llm +- metadata: {} + model_id: sambanova/Meta-Llama-3.2-1B-Instruct + provider_id: sambanova + 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 + provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct + model_type: llm +- metadata: {} + model_id: sambanova/Meta-Llama-3.2-3B-Instruct + provider_id: sambanova + 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 + provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct + model_type: llm +- metadata: {} + model_id: sambanova/Meta-Llama-3.3-70B-Instruct + provider_id: sambanova + 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 + provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct + model_type: llm +- metadata: {} + model_id: sambanova/Llama-3.2-11B-Vision-Instruct + provider_id: sambanova + 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 + provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct + model_type: llm +- metadata: {} + model_id: sambanova/Llama-3.2-90B-Vision-Instruct + provider_id: sambanova + 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 + provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct + model_type: llm +- metadata: {} + model_id: sambanova/Meta-Llama-Guard-3-8B + provider_id: sambanova + provider_model_id: sambanova/Meta-Llama-Guard-3-8B + model_type: llm +- metadata: {} + model_id: meta-llama/Llama-Guard-3-8B + provider_id: sambanova + provider_model_id: sambanova/Meta-Llama-Guard-3-8B + model_type: llm - metadata: embedding_dimension: 384 model_id: all-MiniLM-L6-v2