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 9, 05:00 UTC
Fix grammar (#33121)
Signed-off-by: smashyalts <smashyalts@gmail.com>
smashyalts committed
Jan 31, 2026 at 18:59 UTC
1e86c802d473b4ca4e889a1b2585a05aad7220ba
1 file changed
+1
-1
vllm/v1/worker/cpu_worker.py
+1
-1
@@ -141,7 +141,7 @@ class CPUWorker(Worker):
141
CpuPlatform.get_allowed_cpu_core_node_list()
142
)
143
assert len(allowed_numa_nodes) >= self.parallel_config.world_size, (
144
- f"No enough allowed NUMA nodes to bind threads of "
144
+ f"Not enough allowed NUMA nodes to bind threads of "
145
f"{self.parallel_config.world_size} CPUWorkers. "
146
f"Allowed NUMA nodes are {allowed_numa_nodes}. "
147
"Please try to bind threads manually."