feat(bitnet): implement scaled dot-product attention

[thejhh]

Test Coverage

• Current coverage: 87.1%
• Coverage changes: 86.3% → 87.1%

Performance Metrics

Memory Usage

Tensor Operations

• Allocations per operation:
  • New tensor creation: 120 allocs/op
  • Get/Set operations: 0 allocs/op
  • Parallel operations: 160748 allocs/op
  • BitLinear operations: 3548 allocs/op

BitNet Model Operations

• Allocations per operation:
  • Model weights loading: 1289985000 allocs/op
  • Model inference: N/A (TODO Token Decoding (Inference Loop) #190) allocs/op (TODO Token Decoding (Inference Loop) #190)
  • Ternary weights reading: 48 allocs/op

CPU Performance

Tensor Operations

• Operation timing:
  • Basic operations: 12.86 ns/op
  • Parallel operations: 97222 ns/op
  • Large tensor operations: 1287 ns/op
  • BitLinear operations: 24284088 ns/op

BitNet Model Operations

• Operation timing:
  • Model weights loading: 1228637000 ns/op
  • Model inference: BenchmarkModel_Infer ns/op (TODO Token Decoding (Inference Loop) #190)
  • Ternary weights reading: 3840 ns/op

Areas for Improvement

High Priority

• Optimize memory allocations in model operations (TODO Parallelize with Goroutines #191)
• Implement proper self-attention (TODO Integrate Attention Sublayer (Pre-Norm & Residual) #186)

Medium Priority

• Improve error handling in model operations (TODO Testing & Performance Tuning #192)
• Add more comprehensive benchmarks (TODO Testing & Performance Tuning #192)
• Enhance documentation
• Implement proper feed-forward network (TODO Integrate Feed-Forward Sublayer (Pre-Norm & Residual) #187)

Low Priority

• Consider SIMD optimizations (TODO Parallelize with Goroutines #191)
• Add more model operations (TODO Token Decoding (Inference Loop) #190)
• Improve test organization (TODO Testing & Performance Tuning #192)
• Implement proper output generation (TODO Final Output Layer (LM Head) #189)

Closes #182