foxhunt

Files

jgrusewski 4402dbaf3d audit(dqn-v2): h_s2 audit anchor corrections (post-2c.3+4 reconnaissance)

The 2c.3+4 dispatch agent surfaced two stale anchors in the
2026-04-25 h_s2 consumer audit:

1. Row 11 (IQN target trunk): the kernel referenced as
   `iqn_compute_target_h_s2` in `iqn_dual_head_kernel.cu:1031` is
   actually `iqn_trunk_forward_kernel`, and it is ALREADY ORPHANED
   (loaded into IqnHead::trunk_forward_kernel but never invoked).
   The real IQN target trunk runs through cuBLAS iqn_lt_matmul calls
   in gpu_iqn_head.rs::execute_training_pipeline:820-846 (with a
   cached fast-path at 803-847). Mitigation reduced to: delete dead
   kernel + extract target_encoder_forward_only + replace cuBLAS
   fallback path with that extraction.

2. Row 22 (relu_mask sites): line numbers drifted. Audit said
   5581/5798; current code is 5655/5697/5872. Crucially, 5697 is
   the h_s1 mask, not h_s2/IQN-aux — the audit's "3 sites" claim
   needs verification per site before editing. Updated to the
   current line numbers with a "verify before editing" note.

These are documentation-only corrections. The mitigation strategy
(GRN backward chain replaces relu_mask; target_encoder_forward_only
unifies trunk implementation) is unchanged in spirit.

2026-04-25 12:29:47 +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