[Perf][KV Connector][Mooncake] Pack hybrid/MLA KV into coalesced transfer regions (#57952)
Signed-off-by: staryxchen <staryxchen@tencent.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
This commit is contained in:
co-authored by
Cursor
Yifan Qiao
parent
5dd693122c
commit
faacc13565
File diff suppressed because it is too large
Load Diff
@@ -242,6 +242,8 @@ async def test_build_transfer_params_uses_non_overlapping_physical_pages():
|
||||
kv_cache_config = make_hybrid_gdn_kv_cache_config(block_size=16)
|
||||
worker = object.__new__(MooncakeConnectorWorker)
|
||||
worker.shutdown = noop_shutdown
|
||||
# __new__ skips __init__, where this cache is created. register_kv_caches clears it.
|
||||
worker._prepared_transfer_regions = {}
|
||||
worker.use_mla = False
|
||||
worker.engine = SimpleNamespace(batch_register_memory=lambda *_: 0)
|
||||
worker.is_kv_consumer = True
|
||||
|
||||
Reference in New Issue
Block a user