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

Remove all2all backend envvar (#30363)

Browse Source 
Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Elizabeth Thomas
2025-12-18 13:46:28 -06:00
committed by GitHub
parent 97000a2be7
commit 41b6f9200f
12 changed files with 40 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/config/compilation.py
View File

@@ -899,7 +899,7 @@ class CompilationConfig:
self.compute_bs_to_padded_graph_size()
def set_splitting_ops_for_v1(
self, all2all_backend: str | None = None, data_parallel_size: int | None = None
self, all2all_backend: str, data_parallel_size: int = 1
):
# To compatible with OOT hardware plugin platform (for example vllm-ascend)
# which currently only supports sequence parallelism in eager mode.
@@ -956,11 +956,9 @@ class CompilationConfig:
self.splitting_ops = []
# Disable CUDA graphs for DeepEP high-throughput since its not CG compatible
backend = all2all_backend or envs.VLLM_ALL2ALL_BACKEND
dp_size = data_parallel_size if data_parallel_size is not None else 1
if (
backend == "deepep_high_throughput"
and dp_size > 1
all2all_backend == "deepep_high_throughput"
and data_parallel_size > 1
and self.cudagraph_mode != CUDAGraphMode.NONE
):
# TODO: Piecewise Cuda graph might be enabled