# ------------------------------------------------
# CITATION.cff file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# ------------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "Rllm" in publications use:'
type: software
license: GPL-2.0-or-later
title: 'Rllm: Native Quantized Matrix Products and LLM Inference over ''Rfmalloc''
  Tensors'
version: 0.1.0
abstract: 'The composition layer of the ''Rfmalloc'' ecosystem: it registers ''Rggml''
  (a vendored ''GGML'' build with runtime-SIMD-dispatched quantized kernels) as a
  codec-aware matrix-multiply backend for ''Rfmalloc'', so that products of file-backed,
  quantized tensors run natively in quantized space (weights stay ''Q4_K''/''Q6_K''/...
  encoded, activations are quantized on the fly) instead of being decoded to double
  first. Combined with ''Rgguf'', which exposes ''GGUF'' model weights as borrowed
  typed spans, this lets a larger-than-memory model''s linear layers be multiplied
  through ''GGML''s SIMD-accelerated dot kernels zero-copy from the original model
  mapping. Typed semantic programs written through an R module-and-pipe architecture
  language describe llama, Qwen3.5, LFM2MoE, EmbeddingGemma, ESM-2, Evo 2 and Tiny
  Recursive Models. Bound programs join those serializable graphs to mapped parameter
  storage. Implemented lowerings provide persistent state, pooled embeddings, byte-level
  generation, and CPU or optional CUDA execution; a reference interpreter executes
  the same dataflow through explicit R operator tables and structured recurrence.'
authors:
- family-names: Toure
  given-names: Sounkou Mahamane
  email: sounkoutoure@gmail.com
repository: https://rgenomicsetl.r-universe.dev
repository-code: https://github.com/sounkou-bioinfo/Rfmalloc
commit: 6e05ad03613e89cab2f8bf8eb3a49d553d5a3bed
url: https://sounkou-bioinfo.github.io/Rfmalloc/Rllm/
date-released: '2026-07-18'
contact:
- family-names: Toure
  given-names: Sounkou Mahamane
  email: sounkoutoure@gmail.com