biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Feature] support sequence parallelism using compilation pass (#16155)

Browse Source 
Signed-off-by: cascade812 <cascade812@outlook.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
cascade
2025-04-27 06:29:35 -07:00
committed by GitHub
parent ed7a29d9f8
commit 690fe019f0
21 changed files with 1072 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/distributed/communication_op.py
View File

@@ -19,6 +19,12 @@ def tensor_model_parallel_all_gather(input_: torch.Tensor,
return get_tp_group().all_gather(input_, dim)
def tensor_model_parallel_reduce_scatter(input_: torch.Tensor,
dim: int = -1) -> torch.Tensor:
"""Reduce-Scatter the input tensor across model parallel group."""
return get_tp_group().reduce_scatter(input_, dim)
def tensor_model_parallel_gather(input_: torch.Tensor,
dst: int = 0,
dim: int = -1) -> Optional[torch.Tensor]: