R Observatory: Metrics for edgemodelr version 0.4.5

Balamuta, James Joseph

doi:10.5281/zenodo.21843040

edgemodelr

0.4.5Package record

Local Large Language Model Inference Engine

0packages depend

3.4Kdownloads / year

–test coverage

13/13flavors OK

Overview

About

Maintained by Pawan Rama MaliCRAN page ↗GitHub ↗Issues ↗

Enables R users to run large language models locally using 'GGUF' model files and the 'llama.cpp' inference engine. Provides a complete R interface for loading models, generating text completions, extracting vector representations, and streaming responses in real-time. Includes grammar-constrained generation for structured output, text classification, and retrieval-augmented generation (RAG) pipelines. Supports local inference without requiring cloud APIs or internet connectivity, ensuring complete data privacy and control. Based on the 'llama.cpp' project by Georgi Gerganov (2023) https://github.com/ggml-org/llama.cpp.

Changes in 0.4.5

Bug fixes

**Each completion now starts from an empty context.** The KV cache was never cleared between calls, so every prompt was appended after the previous prompt and answer. Answers depended on earlier calls, and after a few calls the context filled up and every later call failed with "Failed to process prompt". This affected edge_completion(), edge_stream_completion(), edge_grammar_completion() and the functions built on them.
**Generation can be interrupted.** Esc/Ctrl-C now stops a long generation, and timeout_seconds in edge_completion() works: it used to have no effect until the call finished. A timeout raises a "timed out" error. The sampler is freed on every exit path.

Show all changes in 0.4.5Hide the rest of the changes in 0.4.5

**edge_index_documents() no longer hangs.** Splitting any document longer than chunk_size looped forever. chunk_overlap must now be smaller than chunk_size.
**edge_download_model() checks checksums for model names.** With a name from edge_list_models(), expected_sha256, verify_checksum and trust_first_use were silently ignored.
**trust_first_use = TRUE no longer fails after a download by URL.** Storing the hash raised an error once the file had been downloaded.
**edge_install_cuda() no longer times out.** The ~200 MB download used R's default 60 second timeout.
**edge_clean_cache() keeps the CUDA backend and checksum store.** Both were deleted once they were older than max_age_days. The size limit now removes the oldest files until the cache is under the limit; before, some caches could never get under it.
**Prompts longer than the batch size crashed the session.** The prompt was passed to the model in a single call, which llama.cpp only accepts up to n_batch tokens (512 with the default n_ctx = 2048), so any prompt between that and the context size hit an internal assertion, for example a long edge_ask() context. The prompt is now fed in n_batch-sized chunks in completion, streaming and grammar-constrained generation.
**Internal llama.cpp assertions no longer kill the R session.** No ggml abort callback was ever installed, so any GGML_ASSERT/GGML_ABORT hit on R's thread ended in raise(SIGABRT). These now surface as an ordinary R error ("llama.cpp internal error: ...") and the session keeps working. Assertions on ggml worker threads still abort, because R cannot be signalled from another thread.

From NEWS.md in the release

Install

R (CRAN)pak (dev)Ubuntu (r2u)Fedora (COPR)openSUSE (OBS)

install.packages("edgemodelr", repos = "https://cloud.r-project.org/")

Installs the current CRAN release. Prebuilt binaries on Windows and macOS.

if (!requireNamespace("pak", quietly = TRUE))
  install.packages("pak", repos = "https://cloud.r-project.org/")
pak::pak("PawanRamaMali/edgemodelr")

Development version from PawanRamaMali/edgemodelr. Installs pak first if it is not already available.

Release

# enable cranapt (r2u) if it is not already set up, then install
grep -rqs r2u.stat.illinois.edu /etc/apt/sources.list /etc/apt/sources.list.d/ \
  || curl -fsSL https://raw.githubusercontent.com/eddelbuettel/r2u/master/inst/scripts/add_cranapt_noble.sh | sudo bash
sudo apt install -y r-cran-edgemodelr

Fast Ubuntu binaries via r2u (no compilation). The cranapt setup runs once and is skipped when it is already enabled. We list this channel from recorded r2u download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

bspm (used by r2u) also needs make: sudo apt install make

# enable the iucar/cran COPR if it is not already present, then install
ls /etc/yum.repos.d/*iucar*cran*.repo >/dev/null 2>&1 \
  || sudo dnf copr enable -y iucar/cran
sudo dnf install -y R-CRAN-edgemodelr

RPMs from the iucar/cran COPR, rebuilt from CRAN.

For install.packages() integration in R, also: sudo dnf install R-CoprManager

# add the autoCRAN OBS repo (Tumbleweed) if it is missing, then install
zypper -q lr | grep -qi autoCRAN \
  || sudo zypper addrepo https://download.opensuse.org/repositories/devel:/languages:/R:/autoCRAN/openSUSE_Tumbleweed/devel:languages:R:autoCRAN.repo
sudo zypper install -y R-edgemodelr

RPMs auto-built from CRAN on openSUSE OBS (Tumbleweed). We list this channel from recorded autoCRAN download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

Health

CRAN checks

13OK

CRAN check page ↗

Slowest check: 11.6 min · r-oldrel-windows-x86_64

Status changes

OK13 OK2026-10-14
WARNING12 OK, 1 WARNING2026-09-09
ERROR11 OK, 1 ERROR2026-04-25
NOTE11 OK, 3 NOTE2026-04-22
ERROR10 OK, 3 NOTE, 1 ERROR2026-04-18

Show 1 earlier changeHide 1 earlier change

NOTE11 OK, 3 NOTE2026-03-10

Advisories

none known

How this is measured·How advisories are found

Documentation

In release 0.4.5

README· In the repository, left out of the releaseVignettesNoNEWSYes · 100% structured · mentions 0.4.5Citation fileYes · computed when R runs itWebsitenot declared in DESCRIPTION

Help pages: 50 (10 internal)includes a package overview page
Examples that run: 11%4 run in a plain check · 30 never run · 2 hold no code
Exported functions with examples: 90%
Documented parameters: 100%
Return-value docs: 97%
Help pages citing references: 0%

How these are measured

Downloads

3.4K

CRAN downloads in the past year

Rank #6,018 · ~9/day · ~287/mo

Releases R versions

Daily download trend is not available in this view yet.

56830 days

1.4K90 days

3.4K1 year

Compare downloads with other packages →

Also on404 r2u6 autocran

How downloads are counted

Repository

pawanramamali/edgemodelr ↗Account: PawanRamaMali

18Stars

1Forks

4Open issues

0Open PRs

3Releases

294Commits

2Commit identities

294 commits · Last activity 2026-10-13 · Default branch at 0.5.0, ahead of CRAN 0.4.5 (checked 2026-10-21) · Discussions: 1 post

Responsiveness

How these are sampled

PRs merged (all time): 85%
Median days to close, 50 most recently updated closed issues: 3
Median days to close, 50 most recently updated closed PRs: 1

PRs over time

2026-07-14 · 32026-10-13 · 0

How these are measured

PracticesBeta

7 development-tooling and community-health practices detected across 5 families in the upstream repository

Checks run against github.com/pawanramamali/edgemodelr on 2026-10-21.

Continuous integration (2)

GitHub ActionsR CMD check workflow

The R CMD check workflow runs on Linux, macOS and Windows, and on R-devel

Governance and community (1)

The repository owner accepts GitHub Sponsors

Coverage (1)

Coverage reporting (Codecov)

CRAN release process (1)

cran-comments.md

Show all practicesHide 1 practice

Lint, format, editor (2)

lintrRStudio project

How this is detected·Detection ruleset v4 (2026-10-20)

AI coding toolsBeta

This repository shows signs of AI coding tools.

Codexfirst seen 2025-08-30
Pull request it wrote: opened by a project member
Claude Codefirst seen 2025-09-02
Named in .Rbuildignore: .claude, CLAUDE.md
Named in .gitignore: .claude

How this is detected·Detection ruleset v4 (updated 2026-09-27)

Dependencies

Declared dependencies

11 external dependencies (excludes base and recommended)

Installing edgemodelr adds 1 package (1 with compiled code, 1.8 MB of source tarballs). Heaviest: Rcpp 1.8 MB.

Depends (1)

R >= 4.0

Imports (3)

Rcpputilstools

LinkingTo (1)

Rcpp

Suggests (9)

testthat knitr rmarkdown curl shiny openssl jsonlite httr plumber

Enhances (0)

none

Dependency license breakdown →

Reverse dependencies

0direct

0indirect

Nothing depends on this yet.

How these are counted

Code & Tests

People & History

People (8)

Pawan Rama Mali

Georgi Gerganov

Author, Copyright holder · added in 0.1.4

Author of llama.cpp and GGML library

pi6am

Contributor · added in 0.1.4

DRY sampler from Koboldcpp

Dirk Eddelbuettel

Contributor, Reviewer · added in 0.1.4

Bowen Peng

Contributor, Copyright holder · added in 0.1.4

YaRN RoPE implementation

Jeffrey Quesnelle

Contributor, Copyright holder · added in 0.1.4

YaRN RoPE implementation

Ivan Yurchenko

Contributor · added in 0.1.4

Z-algorithm implementation

The ggml authors

Copyright holder · added in 0.1.4

llama.cpp and GGML contributors

Releases (8)

Pick two releases to compare their code metrics.

0.4.5Latest
record
2026-10-12 · current release · diff ↗ ·
3 hours in CRAN's queue
Listed in CRAN's incoming queue from 2026-10-11 22:36 to 2026-10-12 01:57 UTC, in 2 readings.
0.4.3
record
2026-09-08 · diff ↗
0.4.1
record
2026-05-26 · diff ↗ ·
added 19 exports
edge_install_cuda, edge_install_cuda_toolkit, edge_reload_cuda, edge_cuda_info, edge_grammar_completion, edge_json_grammar, edge_extract, edge_classify, edge_embeddings, edge_similarity, edge_model_n_embd, edge_similarity_matrix, edge_map, edge_extract_batch, edge_index_documents, edge_search, edge_ask, edge_chat_completion, edge_serve
R
R 4.6.0 released · 2026-04-24
0.2.0
record
2026-02-26 · diff ↗ ·
added 2 exports
edge_cache_info, edge_simd_info
0.1.6
record
2026-02-07 · diff ↗
0.1.5
record
2026-01-29 · diff ↗
unarchivedReturned to CRAN
2026-01-22
0.1.4
record
2026-01-22 · diff ↗ ·
added 6 exports
edge_download_url, edge_benchmark, edge_find_gguf_models, edge_find_ollama_models, edge_load_ollama_model, edge_small_model_config
archivedRemoved from CRAN
2025-10-02
repeated policy violation Misrepresentation of authorship Repeated submissions with platform-dependent code, incorrectly documented Repeated submissions whilst one is under consideration,
0.1.0
record
2025-09-22
R
R 4.5.0 released · 2025-04-11

Across CRAN, the median accepted release of the past year spent 23 hours in the queue, 90% under 11 days.How queue time is measured

Package metadata

First published: 2025-09-22
Total releases: 8 / 1 yrs
License: MIT + file LICENSE OSI
Minimum R: ≥ 4.0
Download size: 1.0 MB

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("edgemodelr")

The package provides a citation file that builds its entry when R runs it. Run citation() to see it.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

Format

APA

Balamuta, J. J. (2026). R Observatory: Metrics for edgemodelr version 0.4.5 [Data set]. HJJB, LLC. Data release v2026-10-23. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-23, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →