[New model] Qwen-Image-2.1 support (rebase + review follow-ups) (#8099)

Signed-off-by: NumberWan <wantszkin2003@gmail.com>
Signed-off-by: SamitHuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: SamitHuang <285365963@qq.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
This commit is contained in:
authored and GitHub committed 2026-10-07 21:23:59 +08:00
1 parent 8ef77be66e
commit 3dc35694b3
52 files changed
+8058 -136

No files matched your search

+4
View File
@@ -585,6 +585,10 @@ class OrchestratorArgs:
diffusion_attention_config: str | None = None
diffusion_compile_granularity: str | None = None
diffusion_compile_dynamic: bool | None = None
# CUDA graph capture of fixed-shape KV-cache decode steps (Qwen-Image-2.1
# today). None defers to the OmniDiffusionConfig default (enabled);
# --enforce-eager also disables it.
enable_cuda_graph_decode: bool | None = None
cache_backend: str = "none"
cache_config: str | None = None
video_output_transport: dict[str, object] | None = None