anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Diffusion] Add paged KV cache support for HunyuanImage3 DiT on NPU and GPU (#6563)

Browse Source 
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
Signed-off-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
Co-authored-by: zwhzzz0821 <2831474076@qq.com>
This commit is contained in:
Wang fuyinzwhzzz0821zwhzzz0821
 authored and GitHub committed 2026-08-31 10:15:46 +00:00
1 parent 6f16f9546d
commit fe4a2a7477
28 files changed
+1789 -205
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/diffusion/data.py
+2 -3
View File
@@ -1086,10 +1086,9 @@ class OmniDiffusionConfig:
"need_recv_cache", False
):
raise ValueError(
"paged_scheduler Diffusion KV does not support imported AR KV in Phase 1; "
"disable need_recv_cache until connector-aware admission is implemented"
"paged_scheduler Diffusion KV does not support imported AR KV; "
"disable need_recv_cache until connector-aware import is implemented"
)
self.master_port = self._resolve_master_port()
self.request_batch_max_wait_ms = float(self.request_batch_max_wait_ms or 0.0)
if not math.isfinite(self.request_batch_max_wait_ms) or self.request_batch_max_wait_ms < 0: