HF RL Explorer

I'm running a backend group with consensus aware = true and three upstreams, and even when all three are…

I'm running a backend group with consensus aware = true and three upstreams, and even when all three are…: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). I'm running a backend group with consensus aware = true and three upstreams, and even when all three are healthy and in…

The task

I'm running a backend group with consensus_aware = true and three upstreams, and even when all three are healthy and in agreement, almost all RPC traffic lands on the first backend in the config. If I mark that first one unhealthy, I still see requests hit it and fail before…

Part of XiaomiMiMo/MiMo-V2.6-RL-oss.