jgrusewski
6b3a00a0ac
feat(cuda): pipeline improvements — double buffer, weights, collectors
- common_device_functions.cuh: extended shared header for fused ops
- double_buffer.rs: async double-buffered GPU memory transfers
- gpu_weights.rs: unified weight management for fused training
- gpu_experience_collector.rs: streamlined GPU experience collection
- gpu_ppo_collector.rs: PPO collector GPU path improvements
- gpu_curiosity_trainer.rs + kernel: curiosity training on GPU
- dqn_experience_kernel.cu: experience kernel updates
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 23:49:54 +01:00
..
2026-03-13 10:18:35 +01:00
2026-03-11 08:46:58 +01:00
2026-03-12 19:10:18 +01:00
2026-03-14 11:35:15 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-01 22:47:39 +01:00
2026-03-15 23:49:54 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-15 13:45:22 +01:00
2026-03-01 22:47:39 +01:00
2026-03-13 10:18:35 +01:00
2026-03-15 23:04:46 +01:00
2026-03-15 11:59:31 +01:00
2026-03-15 11:59:31 +01:00
2026-03-15 11:59:31 +01:00
2026-03-13 10:18:35 +01:00
2026-03-15 11:59:31 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-15 13:45:22 +01:00
2026-03-15 11:59:31 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-10 13:18:57 +01:00
2026-03-15 11:59:31 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-14 11:35:15 +01:00
2026-03-14 11:35:15 +01:00
2026-03-01 22:47:39 +01:00
2026-03-15 11:59:31 +01:00
2026-03-01 22:47:39 +01:00
2026-03-03 22:16:35 +01:00