[NPU] fix normal DeepEP mode num_tokens_per_rdma_rank error caused by none

[ZeyuanChen2000]

Motivation

If expert_distribution_recorder_mode = "per_token", attributeError is reported in the on_deepep_dispatch_normal method of the expert distribution recorder when the NPU is deployed on a single server.

Modifications

A check for the None value of num_tokens_per_rdma_rank is added to ensure that the RDMA parameter is correctly processed in the single-node environment.

Accuracy Tests

Speed Tests 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 and Merge Process

1. Ping Merge Oncalls to start the process. 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.
   • Common commands include /tag-and-rerun-ci, /tag-run-ci-label, /rerun-failed-ci
4. After green CI and required approvals, ask Merge Oncalls or people with Write permission to merge the PR.

[gemini-code-assist]

Code Review

This pull request adds a null check for num_tokens_per_rdma_rank in the on_deepep_dispatch_normal function to prevent potential attribute errors in environments where RDMA is not initialized. I have no feedback to provide.

[sglang-npu-bot]

/tag-and-rerun-ci

[ZeyuanChen2000]

/rerun-failed-ci

[ZeyuanChen2000]

/rerun-failed-ci

[ZeyuanChen2000]

/rerun-failed-ci

[ZeyuanChen2000]

/rerun-failed-ci

[ZeyuanChen2000]

/rerun-failed-ci