Tiny remove additional args in init_memory_pool (#16158)
This commit is contained in:
@@ -518,7 +518,7 @@ class ModelRunner(ModelRunnerKVCacheMixin):
|
||||
self.configure_kv_cache_dtype()
|
||||
|
||||
# Init memory pool and attention backends
|
||||
self.init_memory_pool(min_per_gpu_memory, server_args)
|
||||
self.init_memory_pool(min_per_gpu_memory)
|
||||
|
||||
# Init max running requests
|
||||
self.max_running_requests = min(
|
||||
|
||||
Reference in New Issue
Block a user