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 11, 00:00 UTC
[CI/Build] Ignore data_parallel_size_local (#30281)
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
Ryan Rock committed
Dec 24, 2025 at 01:40 UTC
ddfac7034e3c30518a0588f568094c8f7a4b80a4
1 file changed
+1
vllm/config/parallel.py
+1
@@ -465,6 +465,7 @@ class ParallelConfig:
465
# Derived/runtime topology, networking, or launch details
466
"data_parallel_rank",
467
"data_parallel_rank_local",
468
+ "data_parallel_size_local",
469
"data_parallel_backend",
470
"data_parallel_external_lb",
471
"data_parallel_hybrid_lb",