Skip to content

GitLab

Unverified Commit 9a7e83e8 authored by tarinkk's avatar tarinkk Committed by GitHub
Browse files

Fix enable chunked prefill for Llama4 (#5575)

parent 417b44eb
Hide whitespace changes
Inline Side-by-side
Showing with 4 additions and 1 deletion
python/sglang/srt/configs/model_config.py
View file @ 9a7e83e8
...@@ -73,8 +73,11 @@ class ModelConfig: ...@@ -73,8 +73,11 @@ class ModelConfig:
) )
if enable_multimodal is None: if enable_multimodal is None:
if self.hf_config.architectures == "Llama4ForConditionalGeneration": if self.hf_config.architectures[0] == "Llama4ForConditionalGeneration":
enable_multimodal = False enable_multimodal = False
logger.info(
"Multimodal is disabled for Llama4. To enable it, set --enable-llama4-multimodal."
)
else: else:
enable_multimodal = True enable_multimodal = True
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment