[EPLB][Bugfix]Reduce unnecessary video memory usage (#6020)

### What this PR does / why we need it?
1.Incorporate the warm up of the EPLB into the profile run.
2.Reusing the same gather buffer

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

### How was this patch tested?
qwen3-235b aime baseline
| dataset | version | metric | mode | vllm-api-general-chat |
|----- | ----- | ----- | ----- | -----|
| aime2024 | 604a78 | accuracy | gen | 86.67 |

eplb The OOM issue does not occur.
| dataset | version | metric | mode | vllm-api-general-chat |
|----- | ----- | ----- | ----- | -----|
| aime2024 | 604a78 | accuracy | gen | 86.67 |

- vLLM version: v0.13.0
- vLLM main:
2c24bc6996

Signed-off-by: shenchuxiaofugui <1311027364@qq.com>

vllm_ascend/worker/model_runner_v1.py

@@ -2266,7 +2266,7 @@ class NPUModelRunner(GPUModelRunner):
                     is_profile=is_profile)
             if is_profile and self.dynamic_eplb:
                 self.model.clear_all_moe_loads()
-            if not is_profile and self.dynamic_eplb:
+            if self.dynamic_eplb:
                 self.eplb_updator.take_update_info_from_eplb_process()
                 self.eplb_updator.forward_end()
             return hidden_states, hidden_states
@@ -2293,6 +2293,7 @@ class NPUModelRunner(GPUModelRunner):
         return output
 
     def profile_run(self) -> None:
+        self.eplb_warmup()
         mc2_tokens_capacity = get_mc2_tokens_capacity()
         if self.max_num_tokens > mc2_tokens_capacity and \
             select_moe_comm_method(mc2_tokens_capacity, self.vllm_config) in {MoECommType.MC2, MoECommType.FUSED_MC2}:

vllm_ascend/worker/worker.py

@@ -366,7 +366,6 @@ class NPUWorker(WorkerBase):
 
     def compile_or_warm_up_model(self) -> None:
         # Note: need to adapt for graph mode.
-        self.model_runner.eplb_warmup()
         warmup_sizes = (self.vllm_config.compilation_config.compile_sizes
                         or []).copy()
         if not self.model_config.enforce_eager: