jgrusewski 3db8c77241 feat(dqn-v2): Plan 4 Task 2c.3c.3 — allocate 8 GRN backward scratch buffers ...

Plan 4 Task 2c.3c.3. Additive only — buffers will be consumed by
2c.3c.4's apply_grn_trunk_backward_raw helper.

8 device scratch buffers (4 per GRN block × 2 blocks):
- grn_h_s{1,2}_d_pre_ln       — [B, hidden]    aliases d_glu_out, d_residual
- grn_h_s{1,2}_d_linear_b_out — [B, 2*hidden]
- grn_h_s{1,2}_d_elu_out      — [B, hidden]
- grn_h_s{1,2}_d_linear_a_out — [B, hidden]

Total ~B × 5 × hidden f32 per block × 2 blocks ≈ B × 5120 floats
(20 KB per sample at SH1=SH2=256). Negligible against existing
~32 MB per-branch cuBLAS workspaces.

Allocated in the trainer's alloc_backward_scratch path alongside
existing per-step backward scratch. dead_code allow on each field
until 2c.3c.4 wires them in.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-25 13:50:45 +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

plan(dqn-v2): Plan 4 Task 2c GRN — further decomposed into 2c.1/2c.2/2c.3+4/2c.5

2026-04-25 11:53:10 +02:00

dqn-gpu-hot-path-audit.md

feat(dqn): Plan 1 Task 9 — atoms_update GPU kernel + AtomsMonitor + delete CPU paths

2026-04-24 18:28:19 +02:00

dqn-named-dims.md

feat(dqn-v2): D.6 plan_isv[6] = remaining_fraction

2026-04-24 20:36:46 +02:00

dqn-wire-up-audit.md

feat(dqn-v2): Plan 4 Task 2c.3c.3 — allocate 8 GRN backward scratch buffers

2026-04-25 13:50:45 +02:00

h_s2_consumers_audit.md

audit(dqn-v2): h_s2 audit anchor corrections (post-2c.3+4 reconnaissance)

2026-04-25 12:29:47 +02:00

isv-slots.md

refactor(dqn-v2): delete legacy CPU-DtoH per_branch_vsn_mean / per_branch_target_drift

2026-04-25 11:02:23 +02:00

ml-supervised-to-dqn-concept-audit.md

delete(dqn): D.7 liquid_mod audit — ODE identity, remove from c51_grad + experience kernels

2026-04-24 20:18:59 +02:00