[diffusion] fix the bug of redundant memory usage on GPU-0

[nono-Sang]

Motivation

Modifications

During multi-GPU inference, GPU0 shows an additional num_gpus - 1 instances of 520MiB memory usage. The code causing this issue is

sglang/python/sglang/multimodal_gen/runtime/loader/component_loader.py

Line 85 in 37c33cc

gpu_mem_before_loading = current_platform.get_available_gpu_memory()

For example, when I use 4 GPUs for inference.

• Before fix:

• After fix:

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review Process

1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments or contact authorized users to do so.
   • /tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci
4. After green CI and required approvals, ask Merge Oncalls to merge.

[gemini-code-assist]

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

[mickqian]

/tag-and-rerun-ci