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

update

Browse source
This commit is contained in:
Xi Yan 2025-03-19 09:49:53 -07:00
parent 42447729e4
commit 0048274ec0
3 changed files with 7 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/_static/llama-stack-spec.html vendored
View file

@ -10328,14 +10328,14 @@
"properties": {
"dataset_id": {
"type": "string",
"description": "The ID of the dataset to be used to run the benchmark."
"description": "The ID of the dataset to be used to run the benchmark. ID obtained through `datasets.register()`"
},
"grader_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of grader ids to use for this benchmark."
"description": "List of grader ids to use for this benchmark. ID obtained through `graders.register()`"
},
"benchmark_id": {
"type": "string",

5
docs/_static/llama-stack-spec.yaml vendored
View file

@ -7084,13 +7084,14 @@ components:
dataset_id:
type: string
description: >-
The ID of the dataset to be used to run the benchmark.
The ID of the dataset to be used to run the benchmark. ID obtained through
`datasets.register()`
grader_ids:
type: array
items:
type: string
description: >-
List of grader ids to use for this benchmark.
List of grader ids to use for this benchmark. ID obtained through `graders.register()`
benchmark_id:
type: string
description: >-

4
llama_stack/apis/benchmarks/benchmarks.py
View file

@ -62,8 +62,8 @@ class Benchmarks(Protocol):
"""
Register a new benchmark. A benchmark consists of a dataset id and a list of grader ids.
:param dataset_id: The ID of the dataset to be used to run the benchmark.
:param grader_ids: List of grader ids to use for this benchmark.
:param dataset_id: The ID of the dataset to be used to run the benchmark. ID obtained through `datasets.register()`
:param grader_ids: List of grader ids to use for this benchmark. ID obtained through `graders.register()`
:param benchmark_id: (Optional) The ID of the benchmark to register. If not provided, an ID will be generated.
:param metadata: (Optional) Metadata for this benchmark for additional descriptions.
"""