jgrusewski
f782ec5a12
perf(cuda): NoisyLinear forward + copy fully GPU-native — zero CPU
noisy_layers.rs:
- forward(): cuBLAS sgemm for W=mu+sigma*epsilon matmul (was CPU loops)
- copy_params_from(): 6x DtoD async memcpy (was 12 PCIe roundtrips)
- Added noisy_add_bias CUDA kernel for bias addition
branching.rs:
- copy_weights_from(): DtoD memcpy for VarStore + NoisyLinear params
- register_mu_in_varstore(): DtoD clone (was host roundtrip)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 17:48:43 +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 17:36:13 +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 17:26:01 +01:00
2026-03-01 22:47:39 +01:00
2026-03-13 10:18:35 +01:00
2026-03-18 17:48:43 +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 10:02:18 +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 17:36:13 +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