Main2main Upgrade vllm commit to 0320 17:00 (#7510)

### What this PR does / why we need it?
Main2main Upgrade vllm commit to 0320 17:00

1. fix vllm refactored `_moe_forward` to call
`runner.forward_impl_chunked()` when `runner.use_dp_chunking` is True.
vllm PR:"[MoE Refactor] DefaultMoERunner simplification
[#33049](https://github.com/vllm-project/vllm/pull/33049)"

2.fix vllm moved the call to `self._set_compile_ranges()` in
`VllmConfig.__post_init__` from **before** `check_and_update_config()`
to **after** it (to allow platforms to lower `max_num_batched_tokens`
first). vllm PR: "fix(xpu): Re-compute compile ranges after
platform-specific config updates"
[#37523](https://github.com/vllm-project/vllm/pull/37523)


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

### How was this patch tested?
NA

- vLLM version: v0.17.0
- vLLM main:
8b6325758c

---------

Signed-off-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Claude Code <noreply@anthropic.com>

vllm_ascend/ascend_config.py

@@ -161,7 +161,7 @@ class AscendConfig:
 
     @staticmethod
     def _get_compile_ranges(compilation_config):
-        return compilation_config.compile_ranges_endpoints
+        return compilation_config.compile_ranges_endpoints or []
 
     @staticmethod
     def _set_compile_ranges(compilation_config, value):

vllm_ascend/ops/fused_moe/fused_moe.py

@@ -259,6 +259,12 @@ class AscendMoERunner(DefaultMoERunner):
         else:
             self.moe_forward = torch.ops.vllm.moe_forward_shared
 
+    @property
+    def use_dp_chunking(self) -> bool:
+        """Ascend uses its own forward_impl path, not the FlashInfer Cutlass
+        chunked path. Always return False to stay on forward_impl."""
+        return False
+
     def forward_impl(
         self,
         layer: torch.nn.Module,