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

dont set num_predict for all providers (#294)

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-10-23 11:44:04 -07:00 • committed by GitHub
parent ffb561070d
commit 21f2e9adf5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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: if params := request.sampling_params:
for attr in {"temperature", "top_p", "top_k", "max_tokens"}: for attr in {"temperature", "top_p", "top_k", "max_tokens"}:
if getattr(params, attr): if getattr(params, attr):
if attr == "max_tokens":
options["num_predict"] = getattr(params, attr)
options[attr] = getattr(params, attr) options[attr] = getattr(params, attr)
if params.repetition_penalty is not None and params.repetition_penalty != 1.0: if params.repetition_penalty is not None and params.repetition_penalty != 1.0: