[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

@@ -130,6 +130,21 @@ class TestCreateDefaultDiffusion:
assert od.diffusion_kv_mode is DiffusionKVCacheMode.PAGED_SCHEDULER
def test_diffusion_kv_sizing_fields_roundtrip(self, monkeypatch):
monkeypatch.setattr(OmniDiffusionConfig, "_resolve_master_port", lambda self: 29500)
od = _roundtrip_diffusion_config(
model="x",
kv_cache_memory_bytes=4096,
gpu_memory_utilization=0.75,
max_num_batched_tokens=2048,
max_model_len=4096,
)
assert od.kv_cache_memory_bytes == 4096
assert od.gpu_memory_utilization == 0.75
assert od.max_num_batched_tokens == 2048
assert od.max_model_len == 4096
def test_qwen_image_edit_plus_sets_generic_multimodal_limit():
od_config = OmniDiffusionConfig(model="Qwen/Qwen-Image-Edit-2511", model_class_name="QwenImageEditPlusPipeline")