[Diffusion] Add native KV cache initialization and Scheduler-managed block allocation (#6094)

Signed-off-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
This commit is contained in:
Yukim1andzwhzzz0821 authored and GitHub committed 2026-08-18 07:00:24 +00:00
1 parent b283215c28
commit 0a1846aa45
33 files changed
+2609 -265

No files matched your search

@@ -118,6 +118,14 @@ def _call_mgr(
)
def test_cache_manager_registers_attention_without_adding_dense_state() -> None:
mgr = _make_cache_mgr()
assert isinstance(mgr, nn.Module)
assert dict(mgr.named_modules())["attn"] is mgr.attn
assert mgr.state_dict() == {}
# ============================================================
# Test 1: No AR KV — basic cache → reuse
# ============================================================