jgrusewski
2d426b5a4f
perf(ppo): eliminate GPU roundtrip in metrics + fix MlDevice type
- Replaced compute_metrics_tensors (CPU→GPU→CPU roundtrip: 3 HtoD +
8 kernels + 4 DtoH) with compute_metrics_cpu (pure f64 two-pass,
data already on host). Zero GPU transfers for metrics.
- Fixed Device→MlDevice type, cuda_stream() extraction pattern
- Removed dead sample_action method (referenced non-existent Tensor type)
- Fixed GpuVarStore::new() to pass stream arg
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 08:31:06 +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
2026-03-18 08:31:06 +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
2026-03-18 08:05:32 +01:00
2026-03-01 22:47:39 +01:00
2026-03-13 10:18:35 +01:00
2026-03-18 08:23:30 +01:00
2026-03-18 07:50:00 +01:00
2026-03-17 22:27:56 +01:00
2026-03-15 11:59:31 +01:00
2026-03-17 22:27:56 +01:00
2026-03-17 22:27:56 +01:00
2026-03-13 10:18:35 +01:00
2026-03-13 10:18:35 +01:00
2026-03-18 07:55:11 +01:00
2026-03-16 21:01:28 +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
2026-03-18 08:05:32 +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
2026-03-18 00:53:47 +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