[PD] Fix staging warmup for GQA prefill decode different tp (#22153)
This commit is contained in:
@@ -776,6 +776,7 @@ class DecodePreallocQueue:
|
||||
)
|
||||
if (
|
||||
self.transfer_queue.enable_staging
|
||||
and hasattr(decode_req.kv_receiver, "require_staging")
|
||||
and decode_req.kv_receiver.require_staging
|
||||
):
|
||||
self.transfer_queue.staging_handler.register_decode_req(
|
||||
|
||||
Reference in New Issue
Block a user