Package: Rllm
Title: Native Quantized Matrix Products and LLM Inference over
        'Rfmalloc' Tensors
Version: 0.1.0
Authors@R: 
    person(given = "Sounkou Mahamane", family = "Toure",
           email = "sounkoutoure@gmail.com", role = c("aut", "cre"))
Description: 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
        'Rfmalloc'-backed tensors, this lets a larger-than-memory
        model's linear layers be multiplied through 'GGML's
        SIMD-accelerated dot kernels zero-copy from the memory-mapped
        payload. A transformer forward-pass graph builder over these
        primitives is planned.
License: GPL (>= 2)
Encoding: UTF-8
Imports: Rfmalloc, Rgguf, Rggml
LinkingTo: Rfmalloc, Rggml
Suggests: tinytest
Remotes: sounkou-bioinfo/Rfmalloc/packages/Rfmalloc,
        sounkou-bioinfo/Rfmalloc/packages/Rgguf,
        sounkou-bioinfo/Rfmalloc/packages/Rggml
Roxygen: list(markdown = TRUE)
RoxygenNote: 7.3.3
Depends: R (>= 4.4.0)
URL: https://github.com/sounkou-bioinfo/Rfmalloc,
        https://sounkou-bioinfo.github.io/Rfmalloc/Rllm/
BugReports: https://github.com/sounkou-bioinfo/Rfmalloc/issues
Repository: https://sounkou-bioinfo.r-universe.dev
Date/Publication: 2026-07-10 06:12:39 UTC
RemoteUrl: https://github.com/sounkou-bioinfo/Rfmalloc
RemoteRef: HEAD
RemoteSha: 921d01f6786a2db38d90a2629c39f56a244b7875
RemoteSubdir: packages/Rllm
NeedsCompilation: yes
Packaged: 2026-07-10 10:09:29 UTC; root
Author: Sounkou Mahamane Toure [aut, cre]
Maintainer: Sounkou Mahamane Toure <sounkoutoure@gmail.com>