CPANTS

Lugh 0.11 Latest

No Core Issues.

meta_yml_has_provides: Add all modules contained in this distribution to the META.yml field 'provides'. Module::Build or Dist::Zilla::Plugin::MetaProvides do this automatically for you.
meta_yml_has_repository_resource: Add a 'repository' resource to the META.yml via 'meta_add' accessor (for Module::Build) or META_ADD parameter (for ExtUtils::MakeMaker).
has_separate_license_file: This is not a critical issue. Currently mainly informative for the CPANTS authors. It might be removed later.
has_security_doc: Add SECURITY(.pod|md). See Software::Security::Policy.
security_doc_contains_contact: Add SECURITY(.pod|md) and add a contact address. See Software::Security::Policy.
has_contributing_doc: Add CONTRIBUTING(.pod|md). See https://docs.github.com/en/communities/setting-up-your-project-for-healthy-contributions/setting-guidelines-for-repository-contributors.

Name	Abstract	Version	View
Lugh	Pure C LLM Inference Engine for Perl (built on ggml)	0.11	metacpan
Lugh::Context	Memory Context for Tensor Allocation	0.11	metacpan
Lugh::Graph	Computation Graph for Tensor Operations	0.11	metacpan
Lugh::Inference	Transformer Forward Pass and Token Generation	0.11	metacpan
Lugh::KVCache	KV Cache for efficient incremental decoding	0.11	metacpan
Lugh::LoRA	Low-Rank Adaptation (LoRA) adapter support for Lugh	0.11	metacpan
Lugh::Model	GGUF Model Loading and Tensor Access	0.11	metacpan
Lugh::Ops	Tensor Operations for Neural Network Computation	0.11	metacpan
Lugh::Prompt	Chat Template Formatting for LLM Conversations	0.11	metacpan
Lugh::Quant	Quantization utilities for Lugh tensors	0.11	metacpan
Lugh::RoPE	RoPE (Rotary Position Embedding) Scaling Configuration	0.11	metacpan
Lugh::Speculative	Speculative decoding for faster LLM inference	0.11	metacpan
Lugh::Tensor	N-Dimensional Tensor with ggml Backend	0.11	metacpan
Lugh::Tokenizer	BPE Tokenizer for Text Encoding and Decoding	0.11	metacpan