Files
xc-llm-ascend/vllm_ascend/ops
Chen Chen 1b47fca0e8 [bugfix] Use FUSED_MC2 MoE comm path for the op dispatch_ffn_combine (#5156)
### What this PR does / why we need it?

- Renames the MoE comm enum value `MoECommType.FUSED_ALLTOALL` to
`MoECommType.FUSED_MC2` and updates all call sites.
- Updates `select_moe_comm_method` to optionally select `FUSED_MC2` on
Ascend A3 when:
  - `enable_expert_parallel=True`
  - quantization is `w8a8_dynamic`
  - `EP <= 16`
  - `dynamic_eplb` is disabled
  - `is_mtp_model = False`
- Replaces the old “fused all-to-all” comm implementation with
`FusedMC2CommImpl`, using `TokenDispatcherWithMC2` /
`PrepareAndFinalizeWithMC2` and `dispatch_ffn_combine`.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: Chen Chen <0109chenchen@gmail.com>
2025-12-18 23:34:31 +08:00
..
2025-12-02 22:10:52 +08:00