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, 03:00 UTC
[Misc] [CI] Fix CI failure caught after merge (#4126)
Cade Daniel committed
Apr 16, 2024 at 17:56 UTC
d150e4f89f9da5b093511227449ad940a9a82a52
1 file changed
+2
vllm/executor/gpu_executor.py
+2
@@ -68,6 +68,7 @@ class GPUExecutor(ExecutorBase):
68
scheduler_config=self.scheduler_config,
69
device_config=self.device_config,
70
cache_config=self.cache_config,
71
+ load_config=self.load_config,
72
local_rank=0,
73
rank=0,
74
distributed_init_method=distributed_init_method,
@@ -82,6 +83,7 @@ class GPUExecutor(ExecutorBase):
83
scheduler_config=self.scheduler_config,
84
device_config=self.device_config,
85
cache_config=self.cache_config,
86
+ load_config=self.load_config,
87
local_rank=0,
88
rank=0,
89
distributed_init_method=distributed_init_method,