[Refactor] Small refactor for group topk (#30562)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
Wentao Ye
2025-12-16 14:50:59 -05:00
committed by GitHub
parent ca702a14dc
commit f21f5ea38c
2 changed files with 10 additions and 4 deletions

View File

@@ -188,7 +188,6 @@ def test_logprobs_bitwise_batch_invariance_bs1_vs_bsN(
llm = LLM(
model=model_name,
tensor_parallel_size=tp_size,
# enable_prefix_caching=False,
max_num_seqs=32,
max_model_len=8192,
dtype="bfloat16", # not everything is supported