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

[diffusion] Support I2I/TI2I/I2V/TI2V warmup && T2I/T2V warmup bug fix (#16922)

Browse Source 
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
HuangJi
2026-01-12 19:40:37 +08:00
committed by GitHub
co-authored by yhyang201 gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent aab640c99f
commit 2dadf63562
6 changed files with 113 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/multimodal_gen/runtime/entrypoints/openai/protocol.py
+1 -1
View File
@@ -72,7 +72,7 @@ class VideoGenerationsRequest(BaseModel):
generator_device: Optional[str] = "cuda"
# SGLang extensions
num_inference_steps: Optional[int] = None
guidance_scale: Optional[float] = None
guidance_scale: Optional[float] = 1.0
guidance_scale_2: Optional[float] = None
true_cfg_scale: Optional[float] = (
None # for CFG vs guidance distillation (e.g., QwenImage)