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

[Core] Add All-to-All communication backend for DCP (#34883)

Browse Source 
Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Signed-off-by: sungsoo ha <hasungsoo@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
sungsoo ha
2026-03-04 07:01:57 -08:00
committed by GitHub
parent ead7bde1ab
commit 6cb901093f
8 changed files with 658 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/engine/arg_utils.py
View File

@@ -85,6 +85,7 @@ from vllm.config.observability import DetailedTraceModules
from vllm.config.parallel import (
All2AllBackend,
DataParallelBackend,
DCPCommBackend,
DistributedExecutorBackend,
ExpertPlacementStrategy,
)
@@ -405,6 +406,7 @@ class EngineArgs:
tensor_parallel_size: int = ParallelConfig.tensor_parallel_size
prefill_context_parallel_size: int = ParallelConfig.prefill_context_parallel_size
decode_context_parallel_size: int = ParallelConfig.decode_context_parallel_size
dcp_comm_backend: DCPCommBackend = ParallelConfig.dcp_comm_backend
dcp_kv_cache_interleave_size: int = ParallelConfig.dcp_kv_cache_interleave_size
cp_kv_cache_interleave_size: int = ParallelConfig.cp_kv_cache_interleave_size
data_parallel_size: int = ParallelConfig.data_parallel_size
@@ -820,6 +822,10 @@ class EngineArgs:
"-dcp",
**parallel_kwargs["decode_context_parallel_size"],
)
parallel_group.add_argument(
"--dcp-comm-backend",
**parallel_kwargs["dcp_comm_backend"],
)
parallel_group.add_argument(
"--dcp-kv-cache-interleave-size",
**parallel_kwargs["dcp_kv_cache_interleave_size"],
@@ -1720,6 +1726,7 @@ class EngineArgs:
worker_cls=self.worker_cls,
worker_extension_cls=self.worker_extension_cls,
decode_context_parallel_size=self.decode_context_parallel_size,
dcp_comm_backend=self.dcp_comm_backend,
dcp_kv_cache_interleave_size=self.dcp_kv_cache_interleave_size,
cp_kv_cache_interleave_size=self.cp_kv_cache_interleave_size,
_api_process_count=self._api_process_count,