[CI] Enable FLASHCOMM1 with layer_sharding and FULL_DECODE_ONLY in ds32 testing (#6115)

### What this PR does / why we need it?

This PR enables FLASHCOMM1 communication optimization with layer
sharding for DeepSeek-V3.2 W8A8 model testing to
  validate PR #5702. The changes include:

  1. Enable FLASHCOMM1: Set VLLM_ASCEND_ENABLE_FLASHCOMM1=1
  improves performance for distributed inference
2. Add layer sharding: Configure layer_sharding: ["q_b_proj", "o_proj"]
4. Update baselines: Adjust performance baselines to reflect the
improvements from FLASHCOMM1 and layer sharding

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

No. This is a CI/test-only change that enables new communication
optimization features for testing purposes.

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
d68209402d

Signed-off-by: guozr <guozr1997@hotmail.com>
Co-authored-by: guozr <guozr1997@hotmail.com>

tests/e2e/multicard/2-cards/test_offline_inference_distributed.py

@@ -242,7 +242,7 @@ def test_qwen3_dense_prefetch_mlp_weight_tp2(model):
 
 
 @patch.dict(os.environ, {"HCCL_OP_EXPANSION_MODE": "AIV"})
-@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_FLASHCOMM1": "0"})
+@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_FLASHCOMM1": "1"})
 @patch.dict(os.environ, {"ASCEND_AGGREGATE_ENABLE": "1"})
 @patch.dict(os.environ, {"HCCL_BUFFSIZE": "1024"})
 def test_deepseek3_2_w8a8_pruning_mtp_tp2_ep():
@@ -262,6 +262,9 @@ def test_deepseek3_2_w8a8_pruning_mtp_tp2_ep():
                         "num_speculative_tokens": 2,
                         "method": "deepseek_mtp"
                     },
+                    additional_config={
+                        "layer_sharding":["q_b_proj", "o_proj"]
+                    },
                     reasoning_parser="deepseek_v3",
                     tokenizer_mode="deepseek_v32") as vllm_model:
         vllm_model.generate_greedy(example_prompts, max_tokens)