chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[diffusion] chore: improve the output_path config and enable the server to return inference duration (#16965)

Browse Source 
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
This commit is contained in:
wxy
2026-01-15 22:31:50 +08:00
committed by GitHub
parent 16831ab6d7
commit d11e2dc6f4
4 changed files with 19 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/multimodal_gen/runtime/entrypoints/openai/protocol.py
View File

@@ -17,6 +17,7 @@ class ImageResponse(BaseModel):
created: int = Field(default_factory=lambda: int(time.time()))
data: List[ImageResponseData]
peak_memory_mb: Optional[float] = None
inference_time_s: Optional[float] = None
class ImageGenerationsRequest(BaseModel):
@@ -60,6 +61,7 @@ class VideoResponse(BaseModel):
error: Optional[Dict[str, Any]] = None
file_path: Optional[str] = None
peak_memory_mb: Optional[float] = None
inference_time_s: Optional[float] = None
class VideoGenerationsRequest(BaseModel):