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 15, 23:30 UTC
[v1] fix parallel config rank (#13445)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Feb 18, 2025 at 12:33 UTC
932b51cedd4b71be5f58dc9704041502f066d7a1
1 file changed
+1
vllm/v1/worker/worker_base.py
+1
@@ -41,6 +41,7 @@ class WorkerBase(WorkerBaseV0):
41
# Configuration storage
42
super().__init__(vllm_config=vllm_config)
43
44
+ self.parallel_config.rank = rank
45
self.local_rank = local_rank
46
self.rank = rank
47
self.distributed_init_method = distributed_init_method