listen_on: 0.0.0.0:* #'localhost' for local connections only, '0.0.0.0' for ipv4 '::' for ipv6
num_experts: 1 #run this many identical experts
expert_cls: ffn #expert type from test_utils.layers, e.g. 'ffn', 'transformer', 'det_dropout' or 'nop'.
hidden_dim: 1024 #main dimension for expert_cls
#num_handlers:  #'server will use this many processes to handle incoming requests
expert_prefix: expert #all expert uids will be {expert_prefix}.{index}
expert_offset: 0 #expert uid will use indices in range(expert_offset, expert_offset + num_experts)
max_batch_size: 16384 #total num examples in the same batch will not exceed this value
#device:  #all experts will use this device in torch notation; default: cuda if available else cpu
no_optimizer: True #if specified, all optimizers use learning rate=0
no_dht: True #if specified, the server will not be attached to a dht
initial_peers: "[]" #a list of peers that will introduce this node to the dht, e.g. [("1.2.3.4", 1337), ("127.0.0.1", 4321)]
#dht_port:  #DHT node will listen on this port
#root_port:  #If this server does not have peers, it will create a virtual dht node on this port. You can then use this node as initial peer.
increase_file_limit: True #On *nix, this will increase the max number of processes a server can spawn before hitting "Too many open files"; Use at your own risk.