[refactor] replace scattered business kwargs with typed request objects and explicit stage boundaries (#7024)

### What this PR does / why we need it?
Refactor `vllm_ascend/ops/fused_moe` to replace scattered MoE business
`**kwargs` with typed request objects and explicit stage boundaries.

- Prepare, dispatch, MLP, and quant stages now have clearer ownership.
- Main MoE path no longer depends on business `kwargs.get(...)` lookups.
- Comm and dispatcher interfaces are request-only on the main path.
- UTs can assert stage-level fields directly instead of inferring
behavior indirectly.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI passed.

---------

Signed-off-by: linfeng-yuan <1102311262@qq.com>
This commit is contained in:
linfeng-yuan
2026-03-20 23:23:57 +08:00
committed by GitHub
parent c860535246
commit 88d03a783f
33 changed files with 2146 additions and 947 deletions

View File

@@ -95,4 +95,4 @@ def test_SiluAndMul_forward_310p(
assert torch.allclose(actual_arg, expected_arg), "swiglu called with unexpected input"
expected_out = (dummy_tensor[..., :h] + 1) * dummy_tensor[..., h:]
assert torch.allclose(out, expected_out)
assert torch.allclose(out, expected_out)