[Platform] Add initial experimental support for Altlas 300I series (#1333)

### What this PR does / why we need it?
Add initial experimental support for Ascend 310P, this patch squash
below PR into one to help validation:

- https://github.com/vllm-project/vllm-ascend/pull/914
- https://github.com/vllm-project/vllm-ascend/pull/1318
- https://github.com/vllm-project/vllm-ascend/pull/1327


### Does this PR introduce _any_ user-facing change?
User can run vLLM on Altlas 300I DUO series

### How was this patch tested?
CI passed with:
- E2E image build for 310P
- CI test on A2 with e2e test and longterm test
- Unit test missing because need a real 310P image to have the test,
will add in a separate PR later.
- Manually e2e test:
- Qwen2.5-7b-instruct, Qwen2.5-0.5b, Qwen3-0.6B, Qwen3-4B, Qwen3-8B:
https://github.com/vllm-project/vllm-ascend/pull/914#issuecomment-2942989322
  - Pangu MGoE 72B


The patch has been tested locally on Ascend 310P hardware to ensure that
the changes do not break existing functionality and that the new
features work as intended.

#### ENV information

CANN, NNAL version: 8.1.RC1
> [!IMPORTANT]  
> PTA 2.5.1 version >= torch_npu-2.5.1.post1.dev20250528 to support NZ
format and calling NNAL operators on 310P

#### Code example

##### Build vllm-ascend from source code

```shell
# download source code as vllm-ascend
cd vllm-ascend
export SOC_VERSION=Ascend310P3
pip install -v -e .
cd ..
```

##### Run offline inference

```python
from vllm import LLM, SamplingParams
prompts = ["水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。",
           "水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。"]

# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.0, top_p=0.95, max_tokens=10)
# Create an LLM.
llm = LLM(
    model="Qwen/Qwen2.5-7B-Instruct",
    max_model_len=4096,
    max_num_seqs=4,
    dtype="float16", # IMPORTANT cause some ATB ops cannot support bf16 on 310P
    disable_custom_all_reduce=True,
    trust_remote_code=True,
    tensor_parallel_size=2,
    compilation_config={"custom_ops":['none', "+rms_norm", "+rotary_embedding"]},
)

# Generate texts from the prompts.
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

```

---------

Signed-off-by: Vincent Yuan <farawayboat@gmail.com>
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: Vincent Yuan <farawayboat@gmail.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: shen-shanshan <467638484@qq.com>

csrc/kernels/pos_encoding_kernels.cpp

@@ -30,7 +30,11 @@ using vllm_ascend::local_mem_copy;
 template <typename scalar_t, bool isNeox> class RotaryEmbedding {
     // NOTE(ganyi): we use 512B as load stride for pipe, need to find another way to
     // retrieve this size from runtime for more Soc support
-    static int constexpr loadSize = 512;
+    #if (__CCE_AICORE__ >= 220)
+        static int constexpr loadSize = 512;
+    #else
+        static int constexpr loadSize = 1024 * 4;
+    #endif
     using dst_t = scalar_t;
     using acc_t = typename AccType<scalar_t>::type;
     // only half tensor have cast instruct to int8, hardcode acc_dst_t as half
@@ -326,7 +330,9 @@ private:
 
 // Declare all the kernel entry here
 ROPE_CUSTOM_KERNEL_DECLARE(half)
-ROPE_CUSTOM_KERNEL_DECLARE(bfloat16_t)
+#if (__CCE_AICORE__ >= 220)
+    ROPE_CUSTOM_KERNEL_DECLARE(bfloat16_t)
+#endif
 
 namespace vllm_ascend {
 
@@ -342,7 +348,7 @@ namespace vllm_ascend {
             reinterpret_cast<TYPE *>(cosSinCache), rotDim, queryStride, keyStride, dstQueryStride, dstKeyStride, \
             numHeads, numKvHeads, headSize, numTokens, loopCnt, blockDim);
 
-// maximum number for runtime to launch a ascendc kernel. 
+// maximum number for runtime to launch a ascendc kernel.
 // we use this to constrain the maximum number of block size
 static const int64_t maxParallelSize = 65535;
 
@@ -357,9 +363,13 @@ extern void rotary_embedding_impl(AscendType type, bool isNeox, void *stream, in
     int blockDim = maxParallelSize > numTokens ? numTokens : maxParallelSize;
     if (type == AscendType::FP16) {
         ROTARY_EMBEDDING_KERNEL_CALL(half);
-    } else if (type == AscendType::BF16) {
+    }
+    #if (__CCE_AICORE__ >= 220)
+    else if (type == AscendType::BF16) {
         ROTARY_EMBEDDING_KERNEL_CALL(bfloat16_t);
-    } else {
+    }
+    #endif
+    else {
         return;
     }
 }