style: cargo fmt --workspace (whitespace/wrapping only, no semantic change)
Whole-workspace rustfmt pass picked up while iterating on Mamba GPU backward work. Verified formatting-only via diff sampling; no logic changed. Co-Authored-By: Claude Sonnet 5 <[email protected]>
This commit is contained in:
@@ -139,10 +139,22 @@ impl RealInferenceEngine {
|
||||
let attn_o = Tensor::randn(&[config.hidden_size, config.hidden_size], &device)
|
||||
.expect("failed to allocate o_proj tensor");
|
||||
|
||||
weights.insert(format!("layers.{layer_idx}.attention.q_proj.weight"), attn_q);
|
||||
weights.insert(format!("layers.{layer_idx}.attention.k_proj.weight"), attn_k);
|
||||
weights.insert(format!("layers.{layer_idx}.attention.v_proj.weight"), attn_v);
|
||||
weights.insert(format!("layers.{layer_idx}.attention.o_proj.weight"), attn_o);
|
||||
weights.insert(
|
||||
format!("layers.{layer_idx}.attention.q_proj.weight"),
|
||||
attn_q,
|
||||
);
|
||||
weights.insert(
|
||||
format!("layers.{layer_idx}.attention.k_proj.weight"),
|
||||
attn_k,
|
||||
);
|
||||
weights.insert(
|
||||
format!("layers.{layer_idx}.attention.v_proj.weight"),
|
||||
attn_v,
|
||||
);
|
||||
weights.insert(
|
||||
format!("layers.{layer_idx}.attention.o_proj.weight"),
|
||||
attn_o,
|
||||
);
|
||||
|
||||
let mlp_gate = Tensor::randn(&[config.hidden_size, config.hidden_size * 4], &device)
|
||||
.expect("failed to allocate gate_proj tensor");
|
||||
@@ -470,7 +482,10 @@ mod tests {
|
||||
assert_eq!(info.name, DEMO_MODEL_NAME);
|
||||
assert_eq!(info.config.vocab_size, VOCAB_SIZE);
|
||||
assert_eq!(info.config.hidden_size, HIDDEN_SIZE);
|
||||
assert!(info.parameter_count > 0, "should report real parameter count");
|
||||
assert!(
|
||||
info.parameter_count > 0,
|
||||
"should report real parameter count"
|
||||
);
|
||||
assert!(info.memory_usage > 0, "should report real memory usage");
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user