jgrusewski b0b06383ad spec: true single-graph — zero CPU on hot path, zero ungraphed launches ...

Single cuGraphExecLaunch per step. PER sampling, gather, training,
priority update ALL as child graph nodes in one parent. Direct-to-trainer
gather eliminates DtoD copies. GPU-side counters eliminate host writes.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-18 23:59:35 +02:00

..

infra

feat(infra): GPU training launcher with local/cloud routing

2026-02-23 11:19:58 +01:00

plans

feat(dqn): enable Branching DQN with 45 factored actions (5×3×3)

2026-03-11 22:00:13 +01:00

superpowers

spec: true single-graph — zero CPU on hot path, zero ungraphed launches

2026-04-18 23:59:35 +02:00