[Bug] shared fusion doesnt work for GLM FP8 model

[hebiao064]

Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
• 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
• 5. Please use English, otherwise it will be closed.

Describe the bug

I need to disable shared fusion expert to make it work: python -m sglang.bench_one_batch --model-path ZP2Test/GLM-4.5-FP8-0724 --tp 8 --batch 32 --input-len 256 --output-len 32 --disable-shared-experts-fusion

Reproduction

.

Environment

.

[hebiao064]

fixed by #8456