A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 10, 16:30 UTC
[UX] Add `-ep` shorthand for `--enable-expert-parallel` (#30890)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Jan 5, 2026 at 22:13 UTC
a68e703c32dc42e10d8887b1452311cc4966adae
1 file changed
+3
-1
vllm/engine/arg_utils.py
+3
-1
@@ -839,7 +839,9 @@ class EngineArgs:
839
**parallel_kwargs["data_parallel_external_lb"],
840
)
841
parallel_group.add_argument(
842
- "--enable-expert-parallel", **parallel_kwargs["enable_expert_parallel"]
842
+ "--enable-expert-parallel",
843
+ "-ep",
844
+ **parallel_kwargs["enable_expert_parallel"],
845
)
846
parallel_group.add_argument(
847
"--all2all-backend", **parallel_kwargs["all2all_backend"]