port deepseekv2 and mtp to main branch (#429)

### What this PR does / why we need it?
This PR ports all the deepseek graph mode code and mtp code from v0.7.3
to the main branch
---------

Signed-off-by: SidaoY <1024863041@qq.com>
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: mengwei805 <mengwei25@huawei.com>
Signed-off-by: libaokui <libaokui@huawei.com>
Signed-off-by: q00832892 <qiaoyang19@huawei.com>
Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
Co-authored-by: SidaoY <1024863041@qq.com>
Co-authored-by: linfeng-yuan <1102311262@qq.com>
Co-authored-by: Yizhou Liu <liuyizhou5@h-partners.com>
Co-authored-by: mengwei805 <mengwei25@huawei.com>
Co-authored-by: libaokui <libaokui@huawei.com>

vllm_ascend/distributed/llmdatadist_connector.py

@@ -462,4 +462,4 @@ class LLMDataDistConnector(KVConnectorBase):
 
     def close(self, ):
         self.llm_datadist_engine.data_dist.unlink_clusters([self.cluster],
-                                                           5000)
+                                                           5000)

vllm_ascend/distributed/parallel_state.py

@@ -0,0 +1,75 @@
+from typing import Optional
+
+import torch
+from vllm.distributed.parallel_state import (GroupCoordinator, get_world_group,
+                                             init_model_parallel_group)
+
+# vllm-ascend will maintain its own EP GroupCoordinator and ETP GroupCoordinator for
+# customize parallel solution
+_EP: Optional[GroupCoordinator] = None
+_ETP: Optional[list[GroupCoordinator]] = None
+
+
+def get_ep_group() -> GroupCoordinator:
+    assert _EP is not None, ("expert model parallel group is not initialized")
+    return _EP
+
+
+def get_etp_group() -> GroupCoordinator:
+    assert _ETP is not None, (
+        "expert tensor parallel group is not initialized")
+    return _ETP
+
+
+def init_ascend_model_parallel(
+    tensor_model_parallel_size: int = 1,
+    pipeline_model_parallel_size: int = 1,
+    expert_tensor_parallel_size: int = 1,
+    backend: Optional[str] = None,
+):
+    assert torch.distributed.is_initialized()
+    world_size: int = torch.distributed.get_world_size()
+    backend = backend or torch.distributed.get_backend(
+        get_world_group().device_group)
+    num_expert_parallel_groups: int = expert_tensor_parallel_size
+    num_expert_tensor_parallel_groups: int = (world_size //
+                                              expert_tensor_parallel_size)
+
+    global _EP
+    assert _EP is None, ("expert parallel group is already initialized")
+    group_ranks = []
+    for i in range(num_expert_parallel_groups):
+        ranks = list(range(i, world_size, num_expert_parallel_groups))
+        group_ranks.append(ranks)
+
+    _EP = init_model_parallel_group(group_ranks,
+                                    get_world_group().local_rank,
+                                    backend,
+                                    group_name="ep")
+
+    group_ranks = []
+    global _ETP
+    assert _ETP is None, (
+        "expert tensor parallel group is already initialized")
+    for i in range(num_expert_tensor_parallel_groups):
+        ranks = list(
+            range(i * expert_tensor_parallel_size,
+                  (i + 1) * expert_tensor_parallel_size))
+        group_ranks.append(ranks)
+
+    _ETP = init_model_parallel_group(group_ranks,
+                                     get_world_group().local_rank,
+                                     backend,
+                                     group_name="etp")
+
+
+def destory_ascend_model_parallel():
+    global _EP
+    if _EP:
+        _EP.destroy()
+    _EP = None
+
+    global _ETP
+    if _ETP:
+        _ETP.destroy()
+    _ETP = None