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

[feature] extend DBO to XBO (#30120)

Browse Source 
Signed-off-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: root <root@hk01dgx028.cm.cluster>
This commit is contained in:
jiangkuaixue123
2025-12-16 13:04:01 +08:00
committed by GitHub
parent c881db364e
commit b9ff4f2a8d
10 changed files with 133 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/engine/arg_utils.py
View File

@@ -408,6 +408,7 @@ class EngineArgs:
enable_expert_parallel: bool = ParallelConfig.enable_expert_parallel
all2all_backend: str | None = ParallelConfig.all2all_backend
enable_dbo: bool = ParallelConfig.enable_dbo
ubatch_size: int = ParallelConfig.ubatch_size
dbo_decode_token_threshold: int = ParallelConfig.dbo_decode_token_threshold
dbo_prefill_token_threshold: int = ParallelConfig.dbo_prefill_token_threshold
disable_nccl_for_dp_synchronization: bool = (
@@ -841,6 +842,10 @@ class EngineArgs:
"--all2all-backend", **parallel_kwargs["all2all_backend"]
)
parallel_group.add_argument("--enable-dbo", **parallel_kwargs["enable_dbo"])
parallel_group.add_argument(
"--ubatch-size",
**parallel_kwargs["ubatch_size"],
)
parallel_group.add_argument(
"--dbo-decode-token-threshold",
**parallel_kwargs["dbo_decode_token_threshold"],
@@ -1557,6 +1562,7 @@ class EngineArgs:
enable_expert_parallel=self.enable_expert_parallel,
all2all_backend=self.all2all_backend,
enable_dbo=self.enable_dbo,
ubatch_size=self.ubatch_size,
dbo_decode_token_threshold=self.dbo_decode_token_threshold,
dbo_prefill_token_threshold=self.dbo_prefill_token_threshold,
disable_nccl_for_dp_synchronization=self.disable_nccl_for_dp_synchronization,