add dispatch_gmm_combine kernel

[kiscad]

What this PR does / why we need it?

This PR introduces the Ascend implementation of the dispatch_ffn_combine kernel and wires it into the vLLM-Ascend runtime, together with follow‑up fixes to ensure the kernel builds and runs correctly in CI.

• Add full host and device implementation of the dispatch_ffn_combine kernel under csrc/dispatch_ffn_combine, including tiling logic, MOE routing helpers, and kernel utilities for quantized FFN dispatch.
• Integrate the new kernel with the PyTorch binding (csrc/torch_binding.cpp, csrc/torch_binding_meta.cpp) and the Ascend runtime (vllm_ascend/ascend_forward_context.py, vllm_ascend/worker/model_runner_v1.py).
• Extend fused MoE communication and token dispatch support in vllm_ascend/ops/fused_moe, adding methods/utilities needed by the new dispatch path.
• Update quantization logic in vllm_ascend/quantization/w8a8_dynamic.py to support the new FFN dispatch flow.
• Fix kernel build issues by adjusting csrc/build_aclnn.sh, CMake configuration, and include/namespace usage in the new kernel files.
• Add an end‑to‑end nightly test tests/e2e/nightly/ops/test_dispatch_ffn_combine.py and helper utilities in vllm_ascend/utils.py to validate the new kernel.

Does this PR introduce any user-facing change?

How was this patch tested?

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

[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.

[gemini-code-assist]

Code Review

This pull request introduces a new dispatch_gmm_combine kernel and refactors some file paths for better organization. My review identified two critical issues with the new kernel implementation. First, in csrc/torch_binding.cpp, there's an unsafe use of c10::string_view when calling a C-style API, which could lead to buffer over-reads or crashes. Second, in csrc/torch_binding_meta.cpp, the meta function for the new operator has a signature mismatch with its schema, which will prevent the operator from being registered correctly. I've provided suggestions to fix both of these critical issues. The rest of the changes, which are mainly include path updates due to file moves, appear to be correct.

[github-actions]

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

[jianzs]

@kiscad Is all the code related to this feature?

[kiscad]

@kiscad Is all the code related to this feature?

Yes, this is a complex kernel including gmm and hccl communication.

[github-actions]

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

[Angazenn]

Not using FUSED_MC2?

[kiscad]

There is an accuracy problem with the FUSED_MC2. We are working on it.

[github-actions]

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

[wangxiyuan]

please remove the chinese note in a follow up PR