From eab3635850ba351af81d76a7b4b3db46ffb7f697 Mon Sep 17 00:00:00 2001
From: wyu0-0 <woshilynn@163.com>
Date: Thu, 11 Sep 2025 22:15:19 +0800
Subject: [PATCH] [Bugfix] Retrieve num_redundant_experts from eplb_config in
 torchair qwen3_moe.py (#2857)

### What this PR does / why we need it?
This PR addresses a configuration retrieval issue related to EPLB
(Expert Parallel Load Balancing) settings in qwen3_moe.py.

The key change is adjusting the source of num_redundant_experts to
correctly fetch from the eplb_config sub-structure within
parallel_config, rather than directly from parallel_config. This aligns
with the updated configuration hierarchy for EPLB-related parameters.

This change references `vllm_ascend/models/qwen3_moe.py`

https://github.com/vllm-project/vllm-ascend/blob/main/vllm_ascend/models/qwen3_moe.py#L255-L257

### Does this PR introduce _any_ user-facing change?
NA

### How was this patch tested?

run bash as follows and test pass
```
source /sfs_turbo/humpy/B080/cann_b080/ascend-toolkit/set_env.sh
source /sfs_turbo/humpy/B080/cann_b080/nnal/atb/set_env.sh
#export HCCL_BUFFSIZE=300

# export HCCL_SOCKET_IFNAME="eth0"
# export TP_SOCKET_IFNAME="eth0"
# export GLOO_SOCKET_IFNAME="eth0"
# export HCCL_IF_IP=33.215.118.231

export VLLM_USE_V1=1
export VLLM_ASCEND_ENABLE_MOE_ALL2ALL_SEQ=1
export TASK_QUEUE_ENABLE=1
# export VLLM_VERSION=0.9.1
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export HCCL_OP_EXPANSION_MODE="AIV"
export HCCL_INTRA_PCIE_ENABLE=1
export HCCL_INTRA_ROCE_ENABLE=0

rm -rf ./.torchair_cache/
rm -rf ./dynamo_*
rm -rf /root/ascend/log/debug/plog/*

python -m vllm.entrypoints.openai.api_server \
    --model=/sfs_turbo/tzq/model/Qwen/Qwen3-235B-A22B/ \
    --served-model-name auto \
    --port 8006 \
    -tp 1 \
    -dp 16 \
    --enable_expert_parallel \
    --max-num-seqs 48 \
    --max-model-len 32768 \
    --gpu-memory-utilization 0.95 \
    --additional-config '{"torchair_graph_config":{"enabled":true,"use_cached_graph":true,"graph_batch_sizes_init":false,"graph_batch_sizes":[1, 8, 16, 24, 48]}, "ascend_scheduler_config":{"enabled":false}, "refresh":true}' \
    --kv-transfer-config \
    '{
        "kv_connector": "SharedStorageConnector",
        "kv_buffer_device": "npu",
        "kv_role": "kv_consumer",
        "kv_parallel_size": 2,
        "kv_port": "20002",
        "engine_id": "decode-'${NODE_RANK}'",
        "kv_rank": 1,
        "kv_connector_extra_config": {
            "prefill": {
                    "dp_size": 1,
                    "tp_size": 16
             },
             "decode": {
                    "dp_size": 16,
                    "tp_size": 1
             }
        }
    }' \
    2>&1 disown

```

- vLLM version: main
- vLLM main:
https://github.com/vllm-project/vllm/commit/0ae43dbf8cb28a299ae724fc742b0c5bcddea868

Signed-off-by: wyu0-0 <woshilynn@163.com>
---
 vllm_ascend/torchair/models/qwen3_moe.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/vllm_ascend/torchair/models/qwen3_moe.py b/vllm_ascend/torchair/models/qwen3_moe.py
index dd4a592..eaed918 100644
--- a/vllm_ascend/torchair/models/qwen3_moe.py
+++ b/vllm_ascend/torchair/models/qwen3_moe.py
@@ -394,7 +394,8 @@ class CustomQwen3MoeModel(Qwen3MoeModel):
         quant_config = vllm_config.quant_config
 
         parallel_config = vllm_config.parallel_config
-        self.num_redundant_experts = parallel_config.num_redundant_experts
+        eplb_config = parallel_config.eplb_config
+        self.num_redundant_experts = eplb_config.num_redundant_experts
         self.padding_idx = config.pad_token_id
         self.vocab_size = config.vocab_size
         self.config = config