From 15652a6b703f059767d75e5a511c4a5accf969ad Mon Sep 17 00:00:00 2001 From: Daoyuan Li <94409450+DaoyuanLi2816@users.noreply.github.com> Date: Sun, 7 Jun 2026 00:34:07 -0700 Subject: [PATCH] [Doc] Fix multimodal torch.compile troubleshooting to not use removed VLLM_TORCH_COMPILE_LEVEL (#44378) Signed-off-by: Daoyuan Li <94409450+DaoyuanLi2816@users.noreply.github.com> Co-authored-by: Cyrus Leung --- docs/design/torch_compile_multimodal.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/design/torch_compile_multimodal.md b/docs/design/torch_compile_multimodal.md index 8b745c8ce2..bb30de56bc 100644 --- a/docs/design/torch_compile_multimodal.md +++ b/docs/design/torch_compile_multimodal.md @@ -88,7 +88,7 @@ If compilation fails for a multimodal model: 1. **Disable and test**: First verify the model works without compilation: ```bash - VLLM_TORCH_COMPILE_LEVEL=0 vllm serve --compilation-config='{"compile_mm_encoder":"false"}' + vllm serve --compilation-config='{"mode":0,"compile_mm_encoder":"false"}' ``` 2. **Check logs**: Enable debug logging to see compilation details: