foxhunt

Files

jgrusewski 9951b8b8cb perf: curiosity training — cuBLAS GEMMs (1085ms → <5ms)

Replace the serial curiosity_fwd_bwd_per_block kernel (CUR_TOTAL_PARAMS=11306
loop iterations × block-level shared-memory reduction per-iteration = 1085ms)
with a cuBLAS GEMM pipeline matching the existing curiosity inference path:

Forward: curiosity_prepare_input → GEMM1(W1) → bias_leaky_relu → GEMM2(W2) → mse_fwd_grad
Backward: gemm_dw(dW2) → bias_grad_reduce(db2) → gemm_dx(d_hidden) → leaky_relu_bwd → gemm_dw(dW1) → bias_grad_reduce(db1)

New CUDA kernels added to curiosity_training_kernel.cu:
  - curiosity_mse_fwd_grad: +b2 in-place, d_pred = 2/CUR_OUTPUT*(pred-target)
  - curiosity_leaky_relu_bwd: gates d_hidden by sign of post-activation hidden
  - curiosity_bias_grad_reduce: sum dy[N, D] over batch → grad_b[D]

GpuCuriosityTrainer rewritten with CuriosityGemm (dedicated cuBLAS+cublasLt
handle) + intermediate buffers (input_buf, hidden_buf, pred_buf, d_hidden_buf).
Reuses forward kernels from curiosity_inference_kernel.cu. Keeps curiosity_adam_step.
Drops partial_grads buffer (max_blocks*11306 floats saved).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-19 12:54:18 +02:00

backtesting

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

common

fix: switch tracing to stderr (unbuffered) — stdbuf has no effect on Rust

2026-04-02 16:29:55 +02:00

config

…

ctrader-openapi

…

data