/ 
Lugh-0.05

Changes for version 0.05 - 2026-01-18

  • Performance Optimizations
  • GPU backend activation
    • Multi-backend support: Metal, BLAS, CUDA, Vulkan, CPU
  • New backend discovery API:
    • Lugh::available_backends() - List all available backends
    • Lugh::backend_count() - Get backend count
    • Lugh::backend_info($name) - Get backend metadata
    • Lugh::backend_available($name) - Check availability
    • Lugh::best_backend() - Get recommended backend
    • Lugh::has_metal() / Lugh::metal_available() - Metal support
  • Backend selection parameter for Lugh::Inference->new(backend => $name)
  • Memory pools for efficient repeated inference:
    • create_memory_pool() - Create reusable compute resources
    • forward_with_pool($pool, \@tokens) - Forward pass with pooled resources
    • Lugh::MemoryPool class with reset() and backend() methods
  • Batch processing for multiple sequences:
    • forward_batch(\@sequences) - Process multiple token sequences
  • New comprehensive performance test file t/09-performance.t
  • Full documentation for new APIs Lugh/Lugh::Inference

Modules

Lugh
Pure C LLM Inference Engine for Perl (built on ggml)
Lugh::Context
Memory Context for Tensor Allocation
Lugh::Graph
Computation Graph for Tensor Operations
Lugh::Inference
Transformer Forward Pass and Token Generation
Lugh::KVCache
KV Cache for efficient incremental decoding
Lugh::Model
GGUF Model Loading and Tensor Access
Lugh::Ops
Tensor Operations for Neural Network Computation
Lugh::Tensor
N-Dimensional Tensor with ggml Backend
Lugh::Tokenizer
BPE Tokenizer for Text Encoding and Decoding

Examples

Other files