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 17, 08:00 UTC
fix-ray (#193)
Zhuohan Li committed
Jun 22, 2023 at 00:21 UTC
2e0d3143844303136c8aefa4c7e7bac30fd26850
1 file changed
+1
-1
vllm/engine/llm_engine.py
+1
-1
@@ -87,7 +87,7 @@ class LLMEngine:
87
worker_cls = ray.remote(
88
num_cpus=0,
89
num_gpus=1,
90
- resources={node_resource: 1e-5},
90
+ resources={node_resource: 1e-3},
91
)(worker_cls).remote
92
93
worker = worker_cls(