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

[Core/DBO][2/N] Dual-Batch Overlap add DeepEP High Throughput support and Prefill support (#24845)

Browse Source 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson
2025-09-23 12:02:10 -04:00
committed by GitHub
parent a903669e10
commit cc1dc7ed6d
19 changed files with 602 additions and 236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/engine/arg_utils.py
View File

@@ -330,6 +330,8 @@ class EngineArgs:
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
eplb_config: EPLBConfig = get_field(ParallelConfig, "eplb_config")
enable_eplb: bool = ParallelConfig.enable_eplb
expert_placement_strategy: ExpertPlacementStrategy = \
@@ -698,6 +700,9 @@ class EngineArgs:
parallel_group.add_argument(
"--dbo-decode-token-threshold",
**parallel_kwargs["dbo_decode_token_threshold"])
parallel_group.add_argument(
"--dbo-prefill-token-threshold",
**parallel_kwargs["dbo_prefill_token_threshold"])
parallel_group.add_argument("--enable-eplb",
**parallel_kwargs["enable_eplb"])
parallel_group.add_argument("--eplb-config",
@@ -1316,6 +1321,7 @@ class EngineArgs:
enable_expert_parallel=self.enable_expert_parallel,
enable_dbo=self.enable_dbo,
dbo_decode_token_threshold=self.dbo_decode_token_threshold,
dbo_prefill_token_threshold=self.dbo_prefill_token_threshold,
enable_eplb=self.enable_eplb,
eplb_config=self.eplb_config,
expert_placement_strategy=self.expert_placement_strategy,