[Refactor] Replace npu_ring_mla with FIA in MLA prefill (#5704)

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

**Refactor: Replace npu_ring_mla with FIA in MLA prefill**

This PR refactors the MLA (Multi-Layer Attention) prefill implementation
by replacing `npu_ring_mla` with `npu_fused_infer_attention_score` (FIA)
operator, unifying the attention backend with the standard attention
implementation.

**Key changes:**

1. **Core prefill refactoring (`mla_v1.py`)**
- Replace `npu_ring_mla` with `npu_fused_infer_attention_score` in
`_forward_prefill` and `_compute_prefill_context`
   - Use TND layout with `softmax_lse_flag=True` for prefill attention
- Use `npu_attention_update` to merge multiple chunk outputs with LSE
(Log-Sum-Exp)
- Change `attn_mask` from `get_final_mla_mask()` to
`get_splitfuse_attn_mask()` for FIA compatibility

2. **Data type handling**
- Add automatic float16 → bfloat16 conversion (FIA with TND layout only
supports bfloat16)
   - Convert output back to original dtype after FIA computation

3. **Metadata optimization**
   - Pre-calculate `actual_seq_lengths_q` in `AscendMLAPrefillMetadata`
- Pre-calculate `chunk_actual_seq_lengths_kv_list` in
`ChunkedContextMetadata`
- Move `torch.cumsum` operations from forward pass to metadata building
phase

4. **CP compatibility (`mla_cp.py`)**
- Add `_ring_mla_mask_builder` to get `npu_ring_mla`-compatible masks
for Context Parallel scenarios
- Add `chunk_actual_seq_lengths_kv_list` field to
`CPChunkedContextMetadata`

**Why we need it:**
- **Backend unification**: Aligns MLA prefill with standard attention
implementation (`attention_v1.py`)
- **Better chunked context support**: FIA + `npu_attention_update`
provides native LSE-based output merging
- **Future compatibility**: Prepares for eventual `npu_ring_mla` removal
across the codebase

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

**No.** This is a pure refactoring with no functional changes - same
behavior, unified backend.

---
- Related issue: #5463 (item 7)
- vLLM version: v0.14.1

Signed-off-by: lico67373 <918688502@qq.com>

tests/e2e/singlecard/test_aclgraph_accuracy.py

@@ -85,8 +85,8 @@ CASE_DS_FULL_DECODE_ONLY = LLMTestCase(
     prompts=PROMPTS_LONG,
     golden_answers=[
         "\n\nSelect an assignment template",
-        "\n\nI'm not sure how to approach this problem. I'm not sure if I should use the law of total probability or if I should use",
-        "\n\n## Answer\n\n$a + b + c = 0$\n\nSolution\n\nLet $x$ be the common root of the equations",
+        "\n\nI'm not sure how to approach this problem. I'm thinking that the area of the triangle is $1/2$ times the area",
+        "\n\n## Answer\n\n$a + b + c = 0$\n\nSolution\n\nLet $x = \\alpha$ be the common root",
     ],
 )
 
@@ -106,8 +106,8 @@ CASE_DS_EX = LLMTestCase(
     prompts=PROMPTS_LONG,
     golden_answers=[
         "\n\nSelect an assignment template",
-        "\n\nI'm not sure how to approach this problem. I'm not sure if I should use the law of total probability or if I should use",
-        "\n\n## Answer\n\n$a + b + c = 0$\n\nSolution\n\nLet $x$ be the common root of the equations",
+        "\n\nI'm not sure how to approach this problem. I'm thinking that the area of the triangle is $1/2$ times the area",
+        "\n\n## Answer\n\n$a + b + c = 0$\n\nSolution\n\nLet $x = \\alpha$ be the common root",
     ],
 )