phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 19:49:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor get_max_tokens and build_options

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-10-23 19:11:04 -07:00
parent 5965ef3979
commit 4a073fcee5
7 changed files with 33 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/adapters/inference/together/together.py
View file

@ -131,7 +131,7 @@ class TogetherInferenceAdapter(
yield chunk
def _get_params(self, request: ChatCompletionRequest) -> dict:
options = get_sampling_options(request)
options = get_sampling_options(request.sampling_params)
if fmt := request.response_format:
if fmt.type == ResponseFormatType.json_schema.value:
options["response_format"] = {