diff --git a/distributions/dependencies.json b/distributions/dependencies.json index 36426e862..eb306adc6 100644 --- a/distributions/dependencies.json +++ b/distributions/dependencies.json @@ -2,9 +2,11 @@ "hf-serverless": [ "aiohttp", "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "faiss-cpu", "fastapi", "fire", @@ -13,6 +15,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -29,9 +32,11 @@ ], "together": [ "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "faiss-cpu", "fastapi", "fire", @@ -39,6 +44,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -56,9 +62,11 @@ ], "vllm-gpu": [ "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "faiss-cpu", "fastapi", "fire", @@ -66,6 +74,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -110,9 +119,11 @@ ], "fireworks": [ "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "faiss-cpu", "fastapi", "fire", @@ -121,6 +132,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -138,9 +150,11 @@ "tgi": [ "aiohttp", "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "faiss-cpu", "fastapi", "fire", @@ -149,6 +163,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -165,10 +180,12 @@ ], "bedrock": [ "aiosqlite", + "autoevals", "blobfile", "boto3", "chardet", "chromadb-client", + "datasets", "faiss-cpu", "fastapi", "fire", @@ -176,6 +193,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -193,9 +211,11 @@ "meta-reference-gpu": [ "accelerate", "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "fairscale", "faiss-cpu", "fastapi", @@ -205,6 +225,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -225,9 +246,11 @@ "meta-reference-quantized-gpu": [ "accelerate", "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "fairscale", "faiss-cpu", "fastapi", @@ -238,6 +261,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -259,9 +283,11 @@ "ollama": [ "aiohttp", "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "faiss-cpu", "fastapi", "fire", @@ -270,6 +296,7 @@ "nltk", "numpy", "ollama", + "openai", "pandas", "pillow", "psycopg2-binary", @@ -287,9 +314,11 @@ "hf-endpoint": [ "aiohttp", "aiosqlite", + "autoevals", "blobfile", "chardet", "chromadb-client", + "datasets", "faiss-cpu", "fastapi", "fire", @@ -298,6 +327,7 @@ "matplotlib", "nltk", "numpy", + "openai", "pandas", "pillow", "psycopg2-binary", diff --git a/docs/source/distributions/self_hosted_distro/bedrock.md b/docs/source/distributions/self_hosted_distro/bedrock.md index e0a5d80d0..ae03c89da 100644 --- a/docs/source/distributions/self_hosted_distro/bedrock.md +++ b/docs/source/distributions/self_hosted_distro/bedrock.md @@ -1,6 +1,3 @@ ---- -orphan: true ---- # Bedrock Distribution ```{toctree} @@ -15,9 +12,12 @@ The `llamastack/distribution-bedrock` distribution consists of the following pro | API | Provider(s) | |-----|-------------| | agents | `inline::meta-reference` | +| datasetio | `remote::huggingface`, `inline::localfs` | +| eval | `inline::meta-reference` | | inference | `remote::bedrock` | | memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | | safety | `remote::bedrock` | +| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | diff --git a/docs/source/distributions/self_hosted_distro/fireworks.md b/docs/source/distributions/self_hosted_distro/fireworks.md index e54302c2e..06a12cb1d 100644 --- a/docs/source/distributions/self_hosted_distro/fireworks.md +++ b/docs/source/distributions/self_hosted_distro/fireworks.md @@ -15,9 +15,12 @@ The `llamastack/distribution-fireworks` distribution consists of the following p | API | Provider(s) | |-----|-------------| | agents | `inline::meta-reference` | +| datasetio | `remote::huggingface`, `inline::localfs` | +| eval | `inline::meta-reference` | | inference | `remote::fireworks` | | memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | | safety | `inline::llama-guard` | +| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | diff --git a/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md b/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md index f9717894f..73d6befd4 100644 --- a/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md +++ b/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md @@ -15,9 +15,12 @@ The `llamastack/distribution-meta-reference-gpu` distribution consists of the fo | API | Provider(s) | |-----|-------------| | agents | `inline::meta-reference` | +| datasetio | `remote::huggingface`, `inline::localfs` | +| eval | `inline::meta-reference` | | inference | `inline::meta-reference` | | memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | | safety | `inline::llama-guard` | +| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | diff --git a/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md b/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md index 3ca161d07..fab9c6cd8 100644 --- a/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md +++ b/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md @@ -15,9 +15,12 @@ The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists | API | Provider(s) | |-----|-------------| | agents | `inline::meta-reference` | +| datasetio | `remote::huggingface`, `inline::localfs` | +| eval | `inline::meta-reference` | | inference | `inline::meta-reference-quantized` | | memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | | safety | `inline::llama-guard` | +| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | diff --git a/docs/source/distributions/self_hosted_distro/ollama.md b/docs/source/distributions/self_hosted_distro/ollama.md index 9f81d9329..405dbdd94 100644 --- a/docs/source/distributions/self_hosted_distro/ollama.md +++ b/docs/source/distributions/self_hosted_distro/ollama.md @@ -15,9 +15,12 @@ The `llamastack/distribution-ollama` distribution consists of the following prov | API | Provider(s) | |-----|-------------| | agents | `inline::meta-reference` | +| datasetio | `remote::huggingface`, `inline::localfs` | +| eval | `inline::meta-reference` | | inference | `remote::ollama` | | memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | | safety | `inline::llama-guard` | +| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | @@ -118,9 +121,9 @@ llama stack run ./run-with-safety.yaml \ ### (Optional) Update Model Serving Configuration -```{note} -Please check the [model_aliases](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/ollama.py#L45) variable for supported Ollama models. -``` +> [!NOTE] +> Please check the [OLLAMA_SUPPORTED_MODELS](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers.remote/inference/ollama/ollama.py) for the supported Ollama models. + To serve a new model with `ollama` ```bash diff --git a/docs/source/distributions/self_hosted_distro/tgi.md b/docs/source/distributions/self_hosted_distro/tgi.md index 59485226e..84b91da38 100644 --- a/docs/source/distributions/self_hosted_distro/tgi.md +++ b/docs/source/distributions/self_hosted_distro/tgi.md @@ -16,9 +16,12 @@ The `llamastack/distribution-tgi` distribution consists of the following provide | API | Provider(s) | |-----|-------------| | agents | `inline::meta-reference` | +| datasetio | `remote::huggingface`, `inline::localfs` | +| eval | `inline::meta-reference` | | inference | `remote::tgi` | | memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | | safety | `inline::llama-guard` | +| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | diff --git a/docs/source/distributions/self_hosted_distro/together.md b/docs/source/distributions/self_hosted_distro/together.md index 5cfc9e805..c458fdb5f 100644 --- a/docs/source/distributions/self_hosted_distro/together.md +++ b/docs/source/distributions/self_hosted_distro/together.md @@ -15,9 +15,12 @@ The `llamastack/distribution-together` distribution consists of the following pr | API | Provider(s) | |-----|-------------| | agents | `inline::meta-reference` | +| datasetio | `remote::huggingface`, `inline::localfs` | +| eval | `inline::meta-reference` | | inference | `remote::together` | | memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | | safety | `inline::llama-guard` | +| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | diff --git a/llama_stack/templates/bedrock/build.yaml b/llama_stack/templates/bedrock/build.yaml index c73db3eae..cd36c320e 100644 --- a/llama_stack/templates/bedrock/build.yaml +++ b/llama_stack/templates/bedrock/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/bedrock/run.yaml b/llama_stack/templates/bedrock/run.yaml index 1f632a1f2..5e1f549de 100644 --- a/llama_stack/templates/bedrock/run.yaml +++ b/llama_stack/templates/bedrock/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: bedrock apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -37,6 +40,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/fireworks/build.yaml b/llama_stack/templates/fireworks/build.yaml index c16e3f5d6..30ea347ae 100644 --- a/llama_stack/templates/fireworks/build.yaml +++ b/llama_stack/templates/fireworks/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/fireworks/run.yaml b/llama_stack/templates/fireworks/run.yaml index 6add39c3a..fecdb1c43 100644 --- a/llama_stack/templates/fireworks/run.yaml +++ b/llama_stack/templates/fireworks/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: fireworks apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -39,6 +42,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/hf-endpoint/build.yaml b/llama_stack/templates/hf-endpoint/build.yaml index 798cb3961..523cf5d83 100644 --- a/llama_stack/templates/hf-endpoint/build.yaml +++ b/llama_stack/templates/hf-endpoint/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/hf-endpoint/run-with-safety.yaml b/llama_stack/templates/hf-endpoint/run-with-safety.yaml index d518f29b8..f024668d5 100644 --- a/llama_stack/templates/hf-endpoint/run-with-safety.yaml +++ b/llama_stack/templates/hf-endpoint/run-with-safety.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: hf-endpoint apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -44,6 +47,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/hf-endpoint/run.yaml b/llama_stack/templates/hf-endpoint/run.yaml index ff4e90606..2a023dd84 100644 --- a/llama_stack/templates/hf-endpoint/run.yaml +++ b/llama_stack/templates/hf-endpoint/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: hf-endpoint apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -39,6 +42,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/hf-serverless/build.yaml b/llama_stack/templates/hf-serverless/build.yaml index 3c03a98c1..af7eb60fe 100644 --- a/llama_stack/templates/hf-serverless/build.yaml +++ b/llama_stack/templates/hf-serverless/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/hf-serverless/run-with-safety.yaml b/llama_stack/templates/hf-serverless/run-with-safety.yaml index e7591bbf0..38488cb55 100644 --- a/llama_stack/templates/hf-serverless/run-with-safety.yaml +++ b/llama_stack/templates/hf-serverless/run-with-safety.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: hf-serverless apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -44,6 +47,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/hf-serverless/run.yaml b/llama_stack/templates/hf-serverless/run.yaml index d7ec02f6a..dd80751eb 100644 --- a/llama_stack/templates/hf-serverless/run.yaml +++ b/llama_stack/templates/hf-serverless/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: hf-serverless apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -39,6 +42,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/meta-reference-gpu/build.yaml b/llama_stack/templates/meta-reference-gpu/build.yaml index ef075d098..300b75b14 100644 --- a/llama_stack/templates/meta-reference-gpu/build.yaml +++ b/llama_stack/templates/meta-reference-gpu/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml index f82e0c938..2a948a51c 100644 --- a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml +++ b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: meta-reference-gpu apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -46,6 +49,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/meta-reference-gpu/run.yaml b/llama_stack/templates/meta-reference-gpu/run.yaml index b125169a3..70f8d3614 100644 --- a/llama_stack/templates/meta-reference-gpu/run.yaml +++ b/llama_stack/templates/meta-reference-gpu/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: meta-reference-gpu apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -40,6 +43,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/meta-reference-quantized-gpu/build.yaml b/llama_stack/templates/meta-reference-quantized-gpu/build.yaml index 961864dac..9d866de18 100644 --- a/llama_stack/templates/meta-reference-quantized-gpu/build.yaml +++ b/llama_stack/templates/meta-reference-quantized-gpu/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml index e1104b623..336e37a49 100644 --- a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml +++ b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: meta-reference-quantized-gpu apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -42,6 +45,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/ollama/build.yaml b/llama_stack/templates/ollama/build.yaml index 106449309..a021e4993 100644 --- a/llama_stack/templates/ollama/build.yaml +++ b/llama_stack/templates/ollama/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/ollama/run-with-safety.yaml b/llama_stack/templates/ollama/run-with-safety.yaml index 6c86677b3..74c3adc8f 100644 --- a/llama_stack/templates/ollama/run-with-safety.yaml +++ b/llama_stack/templates/ollama/run-with-safety.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: ollama apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -38,6 +41,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/ollama/run.yaml b/llama_stack/templates/ollama/run.yaml index b2d6f2c18..36802def0 100644 --- a/llama_stack/templates/ollama/run.yaml +++ b/llama_stack/templates/ollama/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: ollama apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -38,6 +41,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/tgi/build.yaml b/llama_stack/templates/tgi/build.yaml index 0f7602e2f..d90b505df 100644 --- a/llama_stack/templates/tgi/build.yaml +++ b/llama_stack/templates/tgi/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/tgi/run-with-safety.yaml b/llama_stack/templates/tgi/run-with-safety.yaml index ebf082cd6..107a220c1 100644 --- a/llama_stack/templates/tgi/run-with-safety.yaml +++ b/llama_stack/templates/tgi/run-with-safety.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: tgi apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -42,6 +45,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/tgi/run.yaml b/llama_stack/templates/tgi/run.yaml index 352afabb5..ae4f46501 100644 --- a/llama_stack/templates/tgi/run.yaml +++ b/llama_stack/templates/tgi/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: tgi apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -38,6 +41,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/together/build.yaml b/llama_stack/templates/together/build.yaml index a4402ba93..6930b7692 100644 --- a/llama_stack/templates/together/build.yaml +++ b/llama_stack/templates/together/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/together/run.yaml b/llama_stack/templates/together/run.yaml index 855ba0626..20f1ef002 100644 --- a/llama_stack/templates/together/run.yaml +++ b/llama_stack/templates/together/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: together apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -39,6 +42,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite diff --git a/llama_stack/templates/vllm-gpu/build.yaml b/llama_stack/templates/vllm-gpu/build.yaml index 6792a855f..4289296ec 100644 --- a/llama_stack/templates/vllm-gpu/build.yaml +++ b/llama_stack/templates/vllm-gpu/build.yaml @@ -16,4 +16,13 @@ distribution_spec: - inline::meta-reference telemetry: - inline::meta-reference + eval: + - inline::meta-reference + datasetio: + - remote::huggingface + - inline::localfs + scoring: + - inline::basic + - inline::llm-as-judge + - inline::braintrust image_type: conda diff --git a/llama_stack/templates/vllm-gpu/run.yaml b/llama_stack/templates/vllm-gpu/run.yaml index a140ad403..1ec9cf5d6 100644 --- a/llama_stack/templates/vllm-gpu/run.yaml +++ b/llama_stack/templates/vllm-gpu/run.yaml @@ -4,9 +4,12 @@ docker_image: null conda_env: vllm-gpu apis: - agents +- datasetio +- eval - inference - memory - safety +- scoring - telemetry providers: inference: @@ -42,6 +45,18 @@ providers: - provider_id: meta-reference provider_type: inline::meta-reference config: {} + eval: + - provider_id: meta-reference + provider_type: inline::meta-reference + config: {} + datasetio: + - provider_id: huggingface + provider_type: remote::huggingface + config: {} + scoring: + - provider_id: basic + provider_type: inline::basic + config: {} metadata_store: namespace: null type: sqlite