[V1] Revert the default value of enable_chunked_prefill in additional… (#935)

### What this PR does / why we need it?
Revert the default value of enable_chunked_prefill to 'False' in
additional_scheduler_config. In engine v1, enable_chunked_prefill is
forcibly set to True in VllmConfig, which causes it to be perceived as
True in check_and_update_config(). As a result, when the v0 scheduler is
enabled, the chunked prefill feature remains active, leading to the
failure of the v0 scheduler and causing it to fall back to the native v1
scheduling logic.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI passed with new added/existing test.

Signed-off-by: rjg-lyh <1318825571@qq.com>
This commit is contained in:
rjg-lyh
2025-05-23 10:06:50 +08:00
committed by GitHub
parent 46df67a5e9
commit b434f37b46

View File

@@ -202,9 +202,6 @@ class NPUPlatform(Platform):
"ascend_scheduler_config", None) is not None:
additional_scheduler_config = additional_config.get(
"ascend_scheduler_config")
if vllm_config.scheduler_config.enable_chunked_prefill:
additional_scheduler_config[
"enable_chunked_prefill"] = True
from vllm_ascend.core.schedule_config import \
AscendSchedulerConfig
ascend_scheduler_config = AscendSchedulerConfig.initialize_from_config(