[ModelRunner V2] Enable by default for all dense models (#44443)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Wentao Ye
2026-07-02 18:48:57 +08:00
committed by GitHub
co-authored by Nick Hill
parent de2a8fc042
commit a2f713002d
6 changed files with 55 additions and 17 deletions
+7 -1
View File
@@ -84,7 +84,13 @@ def assert_executor(executor, tp_size, pp_size):
assert executor._get_output_rank() == expected_output_rank
if pp_size > 1:
assert executor.vllm_config.max_concurrent_batches == pp_size
expected_concurrent_batches = pp_size + int(
executor.vllm_config.scheduler_config.async_scheduling
and executor.vllm_config.use_v2_model_runner
)
assert (
executor.vllm_config.max_concurrent_batches == expected_concurrent_batches
)
executor.check_health()
assert not executor.is_failed