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

[VLM] feat: accept grid_thws from preprocessed metadata for kimi (#26149)

Browse Source
This commit is contained in:
Mick
2026-05-25 09:10:25 +08:00
committed by GitHub
parent 72c1582d4e
commit 64e2b54a8f
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/models/kimi_k25.py
+7 -3
View File
@@ -680,9 +680,13 @@ class KimiK25ForConditionalGeneration(nn.Module):
pixel_values = torch.cat([item.feature for item in items], dim=0).to( pixel_values = torch.cat([item.feature for item in items], dim=0).to(
device=device, dtype=target_dtype device=device, dtype=target_dtype
) )
grid_thws = torch.concat([item.image_grid_thw for item in items], dim=0).to( image_grid_thws = []
device for item in items:
) grid_thw = item.model_specific_data.get("image_grid_thw")
if grid_thw is None:
grid_thw = item.model_specific_data["grid_thws"]
image_grid_thws.append(grid_thw)
grid_thws = torch.concat(image_grid_thws, dim=0).to(device)
if self.use_data_parallel: if self.use_data_parallel:
image_embeds = run_dp_sharded_mrope_vision_model( image_embeds = run_dp_sharded_mrope_vision_model(