add mla_preprocess kernel (#3226)

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

- Adds the `mla_preprocess` custom kernel to provide an optimized
pre-processing operator for Multi-head Latent Attention (MLA) on Ascend
NPUs.
- Wires the new kernel into the C++ extension pipeline so vLLM can
invoke it directly, cutting Python-side tensor shuffling and memory
copies that previously bottlenecked MLA compilation paths.

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

- No. The change only introduces a low-level kernel; public APIs and
inference behavior remain unchanged.

### How was this patch tested?

- Dedicated Ascend kernels are not covered by our CI yet, so no extra
automated tests were added. Future MLA-focused regression runs will
cover this path.

- vLLM version: v0.11.0

Signed-off-by: Chen Chen <0109chenchen@gmail.com>

.pre-commit-config.yaml

@@ -12,8 +12,8 @@ repos:
     - id: codespell
       args: [
         --toml, pyproject.toml,
-        '--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
-        '-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn'
+        '--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,csrc/mla_preprocess/**,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
+        '-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn,ArchType,AND'
       ]
       additional_dependencies:
         - tomli
@@ -35,6 +35,10 @@ repos:
   rev: v1.32.0
   hooks:
   - id: typos
+    args: [
+      "--force-exclude",
+      "--exclude", "csrc/mla_preprocess/**"
+    ]
 - repo: https://github.com/PyCQA/isort
   rev: 6.0.1
   hooks: