[Bugfix] dynamic eplb does't use fused_alltoall

[shenchuxiaofugui]

What this PR does / why we need it?

The fused alltoall operator itself was not designed or implemented to handle the scenario where tensors are lists, but the weights for dynamic load balancing are in list form.
Therefore, we have disabled this operator when using dynamic load balancing.

Does this PR introduce any user-facing change?

No

How was this patch tested?

After the repair, the service was restarted, and the conversation proceeded normally.
{"id":"","object":"chat.completion","created":,"model":"dsr1","choices":[{"index":0,"message":{"role":"assistant","content":"\nOkay, the user is asking "What is deep learning?" Hmm, this seems like a fundamental question about AI. They might be a complete beginner or someone with some tech background looking to","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"length","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":8,"total_tokens":48,"completion_tokens":40,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}

• vLLM version: v0.12.0
• vLLM main: vllm-project/vllm@ad32e3e

[gemini-code-assist]

Code Review

This pull request addresses a bug where the dynamic expert parallelism load balancer (dynamic_eplb) was incorrectly used with the FUSED_ALLTOALL MoE communication method. The FUSED_ALLTOALL method, which relies on the highly optimized dispatch_ffn_combine kernel, does not support the dynamic expert layout changes that dynamic_eplb introduces. The fix correctly disables FUSED_ALLTOALL when dynamic_eplb is enabled, falling back to the compatible ALLTOALL method. The change is implemented cleanly by introducing a fused_all2all_enable variable, which improves code readability. The fix is correct and necessary for the proper functioning of dynamic load balancing.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[github-actions]

This pull request has conflicts, please resolve those before we can evaluate the pull request.