Files
xc-llm-ascend/vllm_ascend
Shanshan Shen 40c7db6559 [MM][Bugfix] Add MoE verification for multi-modal models (#3897)
### What this PR does / why we need it?

Fix #3891.

The empty of `moe_comm_method` in the above issue is due to the wrong
check for MoE models. To be specific, the method `is_moe_model` only
checks whether a text-only model is a MoE model, without considering
multi-modal models, e.g., `VL` and `Omni`.

Check the config dict recursively to find if it has a key contains
"expert", without checking the model architecture.

It is worth noting that, we can't verify a model by if it contains
`FusedMoE` module because `is_moe_model` is called somewhere before the model loading, e.g., it's called when updating the ACLGraph config in
platform initialization.

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: shen-shanshan <467638484@qq.com>
2025-11-04 09:16:19 +08:00
..
2025-10-25 15:36:32 +08:00
2025-11-03 20:21:07 +08:00
2025-10-25 15:53:01 +08:00