[CI]enable chunked prefill by default (#4569)

set `enable_chunked_prefill` to True for e2e test by default to keep the
same behavior with vLLM

- vLLM version: v0.11.2

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-12-02 08:54:34 +08:00
committed by GitHub
parent 6b9a997076
commit 981a14f8d5
3 changed files with 1 additions and 3 deletions

View File

@@ -118,7 +118,6 @@ def test_eagle_correctness(
spec_model_name = eagle3_model_name() if use_eagle3 else eagle_model_name()
with VllmRunner(
model_name,
enable_chunked_prefill=True,
max_num_seqs=1,
max_num_batched_tokens=2048,
gpu_memory_utilization=0.6,