Merge branch 'main' into eval_api_final

This commit is contained in:
Xi Yan 2025-03-26 12:29:45 -07:00
commit bc0cd07008
79 changed files with 3257 additions and 2358 deletions

View file

@ -37,6 +37,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/bedrock/trace_store.db}
datasetio:

View file

@ -58,6 +58,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/cerebras/trace_store.db}
tool_runtime:

View file

@ -40,6 +40,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ci-tests/trace_store.db}
datasetio:

View file

@ -43,6 +43,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dell/trace_store.db}
datasetio:

View file

@ -39,6 +39,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dell/trace_store.db}
datasetio:

View file

@ -69,6 +69,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dev/trace_store.db}
datasetio:

View file

@ -48,6 +48,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/fireworks/trace_store.db}
datasetio:

View file

@ -43,6 +43,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/fireworks/trace_store.db}
datasetio:

View file

@ -43,6 +43,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/groq/trace_store.db}
datasetio:

View file

@ -48,6 +48,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-endpoint/trace_store.db}
datasetio:

View file

@ -43,6 +43,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-endpoint/trace_store.db}
datasetio:

View file

@ -48,6 +48,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-serverless/trace_store.db}
datasetio:

View file

@ -43,6 +43,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-serverless/trace_store.db}
datasetio:

View file

@ -50,6 +50,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-gpu/trace_store.db}
datasetio:

View file

@ -44,6 +44,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-gpu/trace_store.db}
datasetio:

View file

@ -46,6 +46,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-quantized-gpu/trace_store.db}
datasetio:

View file

@ -17,8 +17,8 @@ from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
from llama_stack.providers.remote.safety.nvidia import NVIDIASafetyConfig
from llama_stack.templates.template import (
DistributionTemplate,
RunConfigSettings,
get_model_registry,
RunConfigSettings,
)
@ -29,6 +29,7 @@ def get_distribution_template() -> DistributionTemplate:
"safety": ["remote::nvidia"],
"agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"],
"post_training": ["remote::nvidia"],
"datasetio": ["inline::localfs"],
"tool_runtime": ["inline::rag-runtime"],
}
@ -87,7 +88,9 @@ def get_distribution_template() -> DistributionTemplate:
]
},
default_models=[inference_model, safety_model],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")],
default_shields=[
ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")
],
default_tool_groups=default_tool_groups,
),
},
@ -96,6 +99,31 @@ def get_distribution_template() -> DistributionTemplate:
"",
"NVIDIA API Key",
),
## Nemo Customizer related variables
"NVIDIA_USER_ID": (
"llama-stack-user",
"NVIDIA User ID",
),
"NVIDIA_DATASET_NAMESPACE": (
"default",
"NVIDIA Dataset Namespace",
),
"NVIDIA_ACCESS_POLICIES": (
"{}",
"NVIDIA Access Policies",
),
"NVIDIA_PROJECT_ID": (
"test-project",
"NVIDIA Project ID",
),
"NVIDIA_CUSTOMIZER_URL": (
"https://customizer.api.nvidia.com",
"NVIDIA Customizer URL",
),
"NVIDIA_OUTPUT_MODEL_DIR": (
"test-example-model@v1",
"NVIDIA Output Model Directory",
),
"GUARDRAILS_SERVICE_URL": (
"http://0.0.0.0:7331",
"URL for the NeMo Guardrails Service",

View file

@ -4,6 +4,7 @@ apis:
- agents
- datasetio
- inference
- post_training
- safety
- telemetry
- tool_runtime
@ -46,6 +47,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
datasetio:

View file

@ -4,6 +4,7 @@ apis:
- agents
- datasetio
- inference
- post_training
- safety
- telemetry
- tool_runtime
@ -41,6 +42,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
datasetio:

View file

@ -41,6 +41,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ollama/trace_store.db}
datasetio:

View file

@ -39,6 +39,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ollama/trace_store.db}
datasetio:

View file

@ -0,0 +1,249 @@
version: '2'
image_name: open-benchmark
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: openai
provider_type: remote::openai
config:
api_key: ${env.OPENAI_API_KEY:}
- provider_id: anthropic
provider_type: remote::anthropic
config:
api_key: ${env.ANTHROPIC_API_KEY:}
- provider_id: gemini
provider_type: remote::gemini
config:
api_key: ${env.GEMINI_API_KEY:}
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
api_key: ${env.GROQ_API_KEY:}
- provider_id: together
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:}
vector_io:
- provider_id: sqlite-vec
provider_type: inline::sqlite-vec
config:
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/sqlite_vec.db
- provider_id: ${env.ENABLE_CHROMADB+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:}
- provider_id: ${env.ENABLE_PGVECTOR+pgvector}
provider_type: remote::pgvector
config:
host: ${env.PGVECTOR_HOST:localhost}
port: ${env.PGVECTOR_PORT:5432}
db: ${env.PGVECTOR_DB:}
user: ${env.PGVECTOR_USER:}
password: ${env.PGVECTOR_PASSWORD:}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/agents_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/open-benchmark/trace_store.db}
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:}
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:}
max_results: 3
- provider_id: tavily-search
provider_type: remote::tavily-search
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:}
max_results: 3
- provider_id: code-interpreter
provider_type: inline::code-interpreter
config: {}
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/registry.db
models:
- metadata: {}
model_id: openai/gpt-4o
provider_id: openai
provider_model_id: openai/gpt-4o
model_type: llm
- metadata: {}
model_id: anthropic/claude-3-5-sonnet-latest
provider_id: anthropic
provider_model_id: anthropic/claude-3-5-sonnet-latest
model_type: llm
- metadata: {}
model_id: gemini/gemini-1.5-flash
provider_id: gemini
provider_model_id: gemini/gemini-1.5-flash
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: groq
provider_model_id: groq/llama-3.3-70b-versatile
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-405B-Instruct
provider_id: together
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
model_type: llm
shields:
- shield_id: meta-llama/Llama-Guard-3-8B
vector_dbs: []
datasets:
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/simpleqa?split=train
metadata: {}
dataset_id: simpleqa
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/mmlu_cot?split=test&name=all
metadata: {}
dataset_id: mmlu_cot
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/gpqa_0shot_cot?split=test&name=gpqa_main
metadata: {}
dataset_id: gpqa_cot
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/math_500?split=test
metadata: {}
dataset_id: math_500
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/bfcl_v3?split=train
metadata: {}
dataset_id: bfcl
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/IfEval?split=train
metadata: {}
dataset_id: ifeval
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/docvqa?split=val
metadata: {}
dataset_id: docvqa
scoring_fns: []
benchmarks:
- dataset_id: simpleqa
scoring_functions:
- llm-as-judge::405b-simpleqa
metadata: {}
benchmark_id: meta-reference-simpleqa
- dataset_id: mmlu_cot
scoring_functions:
- basic::regex_parser_multiple_choice_answer
metadata: {}
benchmark_id: meta-reference-mmlu-cot
- dataset_id: gpqa_cot
scoring_functions:
- basic::regex_parser_multiple_choice_answer
metadata: {}
benchmark_id: meta-reference-gpqa-cot
- dataset_id: math_500
scoring_functions:
- basic::regex_parser_math_response
metadata: {}
benchmark_id: meta-reference-math-500
- dataset_id: bfcl
scoring_functions:
- basic::bfcl
metadata: {}
benchmark_id: meta-reference-bfcl
- dataset_id: ifeval
scoring_functions:
- basic::ifeval
metadata: {}
benchmark_id: meta-reference-ifeval
- dataset_id: docvqa
scoring_functions:
- basic::docvqa
metadata: {}
benchmark_id: meta-reference-docvqa
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
server:
port: 8321

View file

@ -48,6 +48,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/passthrough/trace_store.db}
datasetio:

View file

@ -43,6 +43,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/passthrough/trace_store.db}
datasetio:

View file

@ -67,6 +67,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
tool_runtime:

View file

@ -60,6 +60,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
tool_runtime:

View file

@ -51,6 +51,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/sambanova/trace_store.db}
tool_runtime:

View file

@ -43,6 +43,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/tgi/trace_store.db}
datasetio:

View file

@ -42,6 +42,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/tgi/trace_store.db}
datasetio:

View file

@ -48,6 +48,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
datasetio:

View file

@ -43,6 +43,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
datasetio:

View file

@ -47,6 +47,7 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/vllm-gpu/trace_store.db}
datasetio: