init v0.11.0rc0

vllm_ascend/distributed/parallel_state.py

@@ -11,7 +11,7 @@ from vllm_ascend.ascend_config import get_ascend_config
 # Currently, mc2 op need their own group coordinator.
 _MC2: Optional[GroupCoordinator] = None
 _MLP_TP: Optional[GroupCoordinator] = None
-
+_OTP: Optional[GroupCoordinator] = None
 _LMTP: Optional[GroupCoordinator] = None
 
 
@@ -20,6 +20,12 @@ def get_mc2_group() -> GroupCoordinator:
     return _MC2
 
 
+def get_otp_group() -> GroupCoordinator:
+    assert _OTP is not None, (
+        "output tensor parallel group is not initialized")
+    return _OTP
+
+
 def get_lmhead_tp_group() -> GroupCoordinator:
     assert _LMTP is not None, (
         "lm head tensor parallel group is not initialized")
@@ -74,6 +80,20 @@ def init_ascend_model_parallel(parallel_config: ParallelConfig, ):
                                             backend,
                                             group_name="mlp_tp")
 
+    # If oproj tensor parallel size is set, we will create a group for it.
+    otp_size = get_ascend_config().oproj_tensor_parallel_size
+    if otp_size is not None:
+        group_ranks = []
+        global _OTP
+        num_oproj_tensor_parallel_groups: int = (world_size // otp_size)
+        for i in range(num_oproj_tensor_parallel_groups):
+            ranks = list(range(i * otp_size, (i + 1) * otp_size))
+            group_ranks.append(ranks)
+        _OTP = init_model_parallel_group(group_ranks,
+                                         get_world_group().local_rank,
+                                         backend,
+                                         group_name="otp")
+
     lmhead_tensor_parallel_size = get_ascend_config(
     ).lmhead_tensor_parallel_size
     if lmhead_tensor_parallel_size is not None:
@@ -117,3 +137,8 @@ def destroy_ascend_model_parallel():
     if _LMTP:
         _LMTP.destroy()
     _LMTP = None
+
+    global _OTP
+    if _OTP:
+        _OTP.destroy()
+    _OTP = None