From bf250dd97c76c6d413bac116db84429a3e819ad3 Mon Sep 17 00:00:00 2001 From: TroyHernandez Date: Wed, 22 Jul 2026 16:53:51 -0500 Subject: [PATCH] recommend() docs: pin is consumed by the LTX and Gemma3 loaders only, today --- R/recommend.R | 9 ++++++--- man/recommend.Rd | 9 ++++++--- 2 files changed, 12 insertions(+), 6 deletions(-) diff --git a/R/recommend.R b/R/recommend.R index b89bb77..6aaca39 100644 --- a/R/recommend.R +++ b/R/recommend.R @@ -29,9 +29,12 @@ #' memory pressure into OOM kills. \code{pin} is TRUE when available #' host RAM covers the model's pinned set twice over, FALSE below that, #' FALSE on the cpu tier (nothing stages), and TRUE when RAM cannot be -#' detected (page-locking already fails soft per component). Loaders -#' honor it through their \code{pin} arguments and -#' \code{options(diffuseR.pin_staging)}. +#' detected (page-locking already fails soft per component). Today the +#' LTX pipeline and Gemma3 encoder loaders take \code{pin} arguments +#' and stage pinned weights (see \code{\link{staging_ltx23}}); the +#' image-model loaders do not stage weights yet, so for them \code{pin} +#' is forward-looking policy with no consumer. +#' \code{options(diffuseR.pin_staging)} is the global switch. #' #' @param model "sd21", "sdxl", "flux1", "flux2", "zimage", or "ltx". #' @param vram_gb Numeric or NULL. Free VRAM in GB; auto-detected via diff --git a/man/recommend.Rd b/man/recommend.Rd index dd4e543..f0dc845 100644 --- a/man/recommend.Rd +++ b/man/recommend.Rd @@ -60,9 +60,12 @@ but pinned pages are unswappable, so on small-RAM machines they turn memory pressure into OOM kills. \code{pin} is TRUE when available host RAM covers the model's pinned set twice over, FALSE below that, FALSE on the cpu tier (nothing stages), and TRUE when RAM cannot be -detected (page-locking already fails soft per component). Loaders -honor it through their \code{pin} arguments and -\code{options(diffuseR.pin_staging)}. +detected (page-locking already fails soft per component). Today the +LTX pipeline and Gemma3 encoder loaders take \code{pin} arguments +and stage pinned weights (see \code{\link{staging_ltx23}}); the +image-model loaders do not stage weights yet, so for them \code{pin} +is forward-looking policy with no consumer. +\code{options(diffuseR.pin_staging)} is the global switch. } \examples{