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

[UX] Replace VLLM_ALL2ALL_BACKEND with --all2all-backend (#26732)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-10-13 21:12:52 -04:00
committed by GitHub
parent 8317f72354
commit 3e051bda82
12 changed files with 90 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/engine/arg_utils.py
View File

@@ -371,6 +371,7 @@ class EngineArgs:
data_parallel_hybrid_lb: bool = False
data_parallel_backend: str = ParallelConfig.data_parallel_backend
enable_expert_parallel: bool = ParallelConfig.enable_expert_parallel
all2all_backend: str | None = ParallelConfig.all2all_backend
enable_dbo: bool = ParallelConfig.enable_dbo
dbo_decode_token_threshold: int = ParallelConfig.dbo_decode_token_threshold
dbo_prefill_token_threshold: int = ParallelConfig.dbo_prefill_token_threshold
@@ -763,6 +764,9 @@ class EngineArgs:
parallel_group.add_argument(
"--enable-expert-parallel", **parallel_kwargs["enable_expert_parallel"]
)
parallel_group.add_argument(
"--all2all-backend", **parallel_kwargs["all2all_backend"]
)
parallel_group.add_argument("--enable-dbo", **parallel_kwargs["enable_dbo"])
parallel_group.add_argument(
"--dbo-decode-token-threshold",
@@ -1461,6 +1465,7 @@ class EngineArgs:
data_parallel_backend=self.data_parallel_backend,
data_parallel_hybrid_lb=self.data_parallel_hybrid_lb,
enable_expert_parallel=self.enable_expert_parallel,
all2all_backend=self.all2all_backend,
enable_dbo=self.enable_dbo,
dbo_decode_token_threshold=self.dbo_decode_token_threshold,
dbo_prefill_token_threshold=self.dbo_prefill_token_threshold,