phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 04:50:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove commented code

Browse source
This commit is contained in:
Fred Reiss 2025-02-04 13:11:09 -08:00 • committed by Ashwin Bharambe
parent 5d54c2ee70
commit c08ca19d79
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/inline/inference/vllm/vllm.py
View file

@ -172,8 +172,6 @@ def _convert_sampling_params(
# vLLM allows top-p and top-k at the same time.
vllm_sampling_params = vllm.SamplingParams.from_optional(
max_tokens=(None if sampling_params.max_tokens == 0 else sampling_params.max_tokens),
# Assume that vLLM's default stop token will work
# stop_token_ids=[tokenizer.eos_token_id],
temperature=vllm_temperature,
top_p=vllm_top_p,
top_k=vllm_top_k,