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, 04:45 UTC
[Misc] add vllm_config in __init__ (#19866)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Jun 22, 2025 at 11:10 UTC
4c409cabc2c1c432ba670029990bd59e6bbf1479
1 file changed
+1
vllm/worker/worker_base.py
+1
@@ -509,6 +509,7 @@ class WorkerWrapperBase:
509
"""
510
self.rpc_rank = rpc_rank
511
self.worker: Optional[WorkerBase] = None
512
+ self.vllm_config: Optional[VllmConfig] = None
513
# do not store this `vllm_config`, `init_worker` will set the final
514
# one. TODO: investigate if we can remove this field in
515
# `WorkerWrapperBase`, `init_cached_hf_modules` should be