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

completion() for tgi (#295)

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-10-24 16:02:41 -07:00 • committed by GitHub
parent cb84034567
commit 3e1c3fdb3f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 173 additions and 35 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"] = {