[Feat] Add native Mooncake KV transfer from AR to DiT (#7166)

Signed-off-by: asukaqaq-s <1311722138@qq.com>
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
authored and GitHub committed 2026-09-20 14:44:55 +00:00
1 parent 2d0b03f717
commit 102ba716bf
53 files changed
+2564 -204

No files matched your search

@@ -58,6 +58,7 @@ def _od_config(**overrides):
gpu_memory_utilization=0.9,
kv_cache_memory_bytes=None,
max_num_seqs=1,
diffusion_kv_max_rows_per_request=1,
max_num_batched_tokens=64,
num_gpus=1,
)