gitadmin/foxhunt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(ensemble): DQN adapter tests use correct STATE_DIM input size

Browse Source 
The DQN inference adapter tests hardcoded `vec![0.1; 56]` as the
feature vector, but the DQN model's first shared layer expects
STATE_DIM=96 inputs. cuBLAS gemm_ex was reading 40 elements past the
end of the 56-allocated CudaSlice — uninitialized memory that
happened to give consistent-enough values for the deterministic test
to pass on the pre-change heap layout, and for other tests not to
notice the out-of-bounds read.

Surfaced by the Part 1 checkpoint-load work: adding the CUDA_LOCK
mutex and a new weight_mu_mut method to NoisyLinear shifted
allocation patterns enough that the uninitialized tail now reads
different values between the two predict() calls in
test_dqn_adapter_deterministic, flipping the argmax.

Replace all three `vec![0.1|0.3; 56]` occurrences with
`vec![...; ml_core::state_layout::STATE_DIM]` so the tests actually
exercise the model with in-bounds memory.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
jgrusewski
2026-04-23 10:50:56 +02:00
parent 82dca76dae
commit 5f95cad416
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
crates/ml/src/ensemble/adapters/dqn.rs
View File

@@ -303,7 +303,7 @@ mod tests {
let _guard = CUDA_LOCK.lock().unwrap_or_else(|p| p.into_inner());
let adapter = DqnInferenceAdapter::new_on_device(test_config(), shared_device()).unwrap();
let fv = FeatureVector {
values: vec![0.1; 56],
values: vec![0.1; ml_core::state_layout::STATE_DIM],
timestamp: 1700000000_000_000,
};
let pred = adapter.predict(&fv).unwrap();
@@ -328,7 +328,7 @@ mod tests {
let _guard = CUDA_LOCK.lock().unwrap_or_else(|p| p.into_inner());
let adapter = DqnInferenceAdapter::new_on_device(test_config(), shared_device()).unwrap();
let fv = FeatureVector {
values: vec![0.1; 56],
values: vec![0.1; ml_core::state_layout::STATE_DIM],
timestamp: 1700000000_000_000,
};
let pred1 = adapter.predict(&fv).unwrap();
@@ -361,7 +361,7 @@ mod tests {
}
let fv = FeatureVector {
values: vec![0.3; 56],
values: vec![0.3; ml_core::state_layout::STATE_DIM],
timestamp: 1700000000,
};
let pred1 = adapter.predict(&fv).expect("first predict");