[Core][Refactor][Diffusion] refactor request scheduler's admission wait policy (#5843)
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
1 parent
c588208cc6
commit
33dd9a5a3e
13 files changed
+253
-54
No files matched your search
@@ -146,7 +146,7 @@ def _make_engine_with_loop(
|
||||
engine.executor = _ConcurrencyTrackingExecutor(rpc_delay=rpc_delay)
|
||||
|
||||
sched = RequestScheduler()
|
||||
sched.initialize(SimpleNamespace(max_num_seqs=1))
|
||||
sched.initialize(SimpleNamespace(max_num_seqs=1, request_batch_max_wait_ms=0.0))
|
||||
engine.scheduler = sched
|
||||
engine.step_execution = False
|
||||
engine.supports_request_batch = False
|
||||
|
||||
Reference in new issue
Block a user