Disaggregate prefill for kv cache register style (#950)

### What this PR does / why we need it?
This PR adopt `LLMDataDist` for kv cache register and `pull_blocks`
style disaggregate prefill implementation. The interface implementation
mainly follows the design of NIXL PR
https://github.com/vllm-project/vllm/pull/17751/files#diff-7eaad0b7dee0626bf29d10081b0f0c5e3ea15a4af97e7b182a4e0d35f8346953
.

This PR can be test with the following step:
- Generate the rank table for all machine.
- execute`toy_proxy.py` to launch the disaggregate prefill proxy server,
specify the prefill ip, port and the decode ip, port
- Run the prefill server and decode server.
- send the request to the disaggregate prefill proxy

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

### How was this patch tested?


- vLLM version: v0.9.2
- vLLM main:
8d0a01a5f2

---------

Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
Signed-off-by: machenglong <machenglong_yewu@cmss.chinamobile.com>
Signed-off-by: liziyu179 <3475441767@qq.com>
Signed-off-by: underfitc <hucong24@huawei.com>
Signed-off-by: zouyida2052 <zouyida@huawei.com>
Signed-off-by: liziyu <liziyu16@huawei.com>
Signed-off-by: underfituu <hzhucong@163.com>
Co-authored-by: machenglong <machenglong_yewu@cmss.chinamobile.com>
Co-authored-by: liziyu179 <3475441767@qq.com>
Co-authored-by: underfitc <hucong24@huawei.com>
Co-authored-by: zouyida2052 <zouyida@huawei.com>
Co-authored-by: liziyu <liziyu16@huawei.com>
Co-authored-by: underfituu <hzhucong@163.com>

tests/ut/attention/test_attention_v1.py

@@ -251,7 +251,10 @@ class TestAscendAttentionBackendImpl(TestBase):
         query = torch.randn(10, 8 * 64)
         key = torch.randn(10, 8 * 64)
         value = torch.randn(10, 8 * 64)
-        kv_cache = torch.ones(1, 1, 10, 8, 64, dtype=torch.int8)
+        k_cache = torch.ones(1, 10, 8, 64, dtype=torch.int8)
+        v_cache = torch.ones(1, 10, 8, 64, dtype=torch.int8)
+        kv_cache = [k_cache, v_cache]
+        ret_value = torch.ones(1, 1, 10, 8, 64, dtype=torch.int8)
 
         metadata = MagicMock()
         metadata.num_actual_tokens = torch.randn(10, 8 * 64)
@@ -261,7 +264,7 @@ class TestAscendAttentionBackendImpl(TestBase):
         metadata.query_lens = torch.randn(10, 8 * 64)
         layer = self.layer
         layer.quant_method = MagicMock()
-        layer.quant_method.apply.return_value = kv_cache
+        layer.quant_method.apply.return_value = ret_value
 
         output = self.impl.forward(layer,
                                    query,