[Vulkan] Allow assert-only SymBool chains in the partitioner

Summary:

## Ulterior Motive

Restore the "Test WebGPU Native (Dawn)" workflow on `main`, which has failed on every commit since "[Vulkan] Keep unrepresentable and symbolic scalars out of the delegate (pytorch#23247)".

## Rationale

**What**: The Vulkan partitioner no longer applies its SymBool/SymFloat rejection to assert ops (`_assert_scalar`, `sym_constrain_range_for_size`) or to nodes whose only users are assert ops.

**Why**: pytorch#23247 rejects every node that produces or consumes a SymBool. Models that guard an `.item()` value with `torch._check` produce `u <= N` / `u >= 0` comparisons feeding `_assert_scalar`. Rejecting them cascades through the new "symbolic scalar has an unsupported consumer" check to the `_local_scalar_dense` producer, splitting the graph into multiple delegates. `test_rope_hf.py` then fails with `AssertionError: expected one delegate, got 2`. Asserts are stripped by `RemoveAssertsTransform` during preprocessing, so these SymBool values never need a runtime representation.

## Details

- Assert-only SymBool chains
  - **Before**: Comparisons and asserts rejected; `.item()` producer rejected as a consequence; graph split into multiple delegates.
  - **After**: Delegated, then removed during preprocessing; graph stays in one delegate.
- SymBool/SymFloat values feeding non-assert ops
  - **Before**: Rejected.
  - **After**: Unchanged (still rejected).

Test Plan:

## Observed Results

| Validation | Device | Result |
|---|---|---|
| Vulkan partition count for `DynamicHfRope` (`test_rope_hf.py`), parent commit | macOS (Apple Silicon) host, partitioner only | 2 partitions; skip logs match the CI failure |
| Vulkan partition count for `DynamicHfRope`, this commit | macOS (Apple Silicon) host, partitioner only | 1 partition, no skipped nodes |
| `test_rope_hf.py` end-to-end ("Test WebGPU Native (Dawn)") | — | Not run: needs the Dawn/SwiftShader runtime; relying on CI |
| `backends/vulkan/test/test_vulkan_dynamic.py` | — | Not run: needs the Vulkan runtime; relying on CI |
| Lint | — | Not run: lint tooling not installed locally; relying on CI |

## Reproduction Guide

### Setup

```bash
git clone https://github.com/pytorch/executorch.git
cd executorch
./install_executorch.sh
```

### Count Vulkan partitions for the dynamic HF RoPE model

```bash
cat > /tmp/count_partitions.py <<'PY'
import torch
from executorch.exir import to_edge
from executorch.backends.vulkan.partitioner.vulkan_partitioner import VulkanPartitioner
from executorch.backends.webgpu.test.ops import test_rope_hf as t

inputs = t._dynamic_inputs()
with torch._dynamo.config.patch(capture_scalar_outputs=True):
    ep = torch.export.export(t.DynamicHfRope().eval(), inputs)
res = VulkanPartitioner().partition(to_edge(ep).exported_program())
tags = {
    n.meta["delegation_tag"]
    for n in res.tagged_exported_program.graph.nodes
    if n.meta.get("delegation_tag")
}
print("partitions:", len(tags))
PY
python /tmp/count_partitions.py 2>&1 | grep -E "Vulkan Partitioner|partitions:"
```

Run once on this commit (expect `partitions: 1`) and once on its parent (`git checkout HEAD~1`, expect `partitions: 2` plus "symbolic float or bool values are not supported" skip logs).

Reviewers:

This PR was authored with Claude Code.

Author: SS-JIA

backends/vulkan/partitioner/vulkan_partitioner.py

@@ -14,6 +14,7 @@
 
 import torch
 
+from executorch.backends.vulkan._passes.remove_asserts import RemoveAssertsTransform
 from executorch.backends.vulkan.op_registry import (
     get_op_features,
     has_impl,
@@ -229,7 +230,15 @@ def _check_node_support(self, node: torch.fx.Node) -> bool:  # noqa: C901
             self.log_skip(node, "fusable pattern requires 64-bit tensor downcasting")
             return False
 
-        if any(
+        # Asserts and the symbolic comparisons feeding them are removed during
+        # preprocessing, so their SymBool values never need to be represented.
+        is_assert_chain = node.target in RemoveAssertsTransform.assert_ops or (
+            len(node.users) > 0
+            and all(
+                user.target in RemoveAssertsTransform.assert_ops for user in node.users
+            )
+        )
+        if not is_assert_chain and any(
             isinstance(arg.meta.get("val"), (torch.SymFloat, torch.SymBool))
             for arg in [node, *node.all_input_nodes]
         ):