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, 08:30 UTC
[Misc] Remove duplicate init for self.vllm_config (#18896)
Signed-off-by: googs1025 <googs1025@gmail.com>
CYJiang committed
May 30, 2025 at 01:26 UTC
d58f9c7f7a3bd29a6ab3f6a5a740299a4555cbc2
1 file changed
-1
vllm/v1/engine/core.py
-1
@@ -123,7 +123,6 @@ class EngineCore:
123
logger.info("Batch queue is enabled with size %d",
124
self.batch_queue_size)
125
self.batch_queue = queue.Queue(self.batch_queue_size)
126
- self.vllm_config = vllm_config
126
127
def _initialize_kv_caches(
128
self, vllm_config: VllmConfig) -> tuple[int, int, KVCacheConfig]: