phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 15:23:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

dont set num_predict for all providers

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-10-23 10:54:25 -07:00
parent ffb561070d
commit dbbfaf68cd
1 changed files with 0 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -34,8 +34,6 @@ def get_sampling_options(request: ChatCompletionRequest) -> dict:
if params := request.sampling_params:
for attr in {"temperature", "top_p", "top_k", "max_tokens"}:
if getattr(params, attr):
if attr == "max_tokens":
options["num_predict"] = getattr(params, attr)
options[attr] = getattr(params, attr)
if params.repetition_penalty is not None and params.repetition_penalty != 1.0: