# Self-directed benchmark: ssm_mamba strategy stress test

- Paper ID: self.20260429151831.129
- Hypothesis: Benchmark a simplified recovered baseline against an ablated variant.
- Plan: Run the deterministic recovery benchmark and capture VRAM plus throughput telemetry.
- Expected Signal: Recovered benchmark should execute and emit standard telemetry fields.
- Concept Combo: recovery_baseline
- Note: Generated fallback because the architect returned no content.

--- ATTEMPT: initial (code=0) ---
--- STDOUT ---
--- RUNTIME PROFILE ---
Device policy: gpu_required
Torch: 2.11.0+rocm7.1
Accelerator backend: rocm
Torch CUDA build: None
Torch HIP build: 7.1.52802
CUDA available: True
CUDA device count: 1
CUDA device[0]: AMD Radeon 890M
Accelerator memory total: 92160.0 MB
Accelerator memory used: 54994.7 MB
Recommended autocast dtype: bf16
Recommended DataLoader pin_memory: True
Recommended DataLoader num_workers: 12
Recommended starting batch size: 64
Recommended CPU threads: 24
/dev/kfd present: True

--- Testing Self-directed benchmark ssm_mamba strategy stress test ---
[Pre-Norm (Recovered Baseline)]
VRAM_USAGE: 35.25MB
TOKENS_PER_SEC: 548152.10
Phenomena Detection:
 - Max Outlier Magnitude: 0.9998
 - Mean Activation: 0.0004
[Post-Norm (Recovered Ablation)]
VRAM_USAGE: 34.50MB
TOKENS_PER_SEC: 2317223.09
Phenomena Detection:
 - Max Outlier Magnitude: 0.9999
 - Mean Activation: -0.0001
VERIFIED: Recovery benchmark executed; ablated mode used less or equal VRAM in this run.

--- STDERR ---


--- HUMAN SUMMARY (LAYMAN) ---
What this test was trying to prove: Testing Self-directed benchmark ssm_mamba strategy stress test
Result: The test completed successfully.
Pre-Norm (Recovered Baseline): speed=548152.10 tokens/sec, activation outlier=0.9998, mean activation=0.0004, vram=35.25MB
Benchmark script conclusion: VERIFIED: Recovery benchmark executed; ablated mode used less or equal VRAM in this run.