You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
petals/src/petals/client/routing
Alexander Borzunov 351e96bc46
Penalize servers that use relays during rebalancing (#428)
Servers accessible only via relays may introduce issues if they are the only type of servers holding certain blocks. Specifically, a connection to such servers may be unstable or opened after a certain delay.

This PR changes their self-reported throughput, so that the rebalancing algorithm prefers to put directly available servers for hosting each block.
11 months ago
..
__init__.py Optimize RemoteSequenceManager (#106) 2 years ago
sequence_info.py Report inference, forward, and network RPS separately (#358) 11 months ago
sequence_manager.py Penalize servers that use relays during rebalancing (#428) 11 months ago
spending_policy.py Optimize RemoteSequenceManager (#106) 2 years ago