Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,044 Open 11,019 Closed
1,044 Open 11,019 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Remove redundant CUDA copies after gated_delta_net. ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23940 opened May 31, 2026 by gaugarg-nv Contributor Loading…
6
speculative : fix out-of-bounds read in ngram-map on prompt shrink
#23936 opened May 31, 2026 by o7si Contributor Loading…
1
cuda: reset cuda context after reading memory size ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23935 opened May 31, 2026 by 0cc4m Contributor Loading…
common : retry HTTP requests over IPv4 when IPv6 connect fails
#23933 opened May 31, 2026 by CptTZ Loading…
common: use physical core count for --threads -1 default
#23932 opened May 31, 2026 by Oxygen56 Loading…
1
ci: remove redundant or duplicate jobs devops improvements to build systems and github actions
#23927 opened May 31, 2026 by netrunnereve Collaborator Loading…
3
opencl: fix compiler warnings for non-adreno path ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#23922 opened May 30, 2026 by lhez Contributor • Draft
server: handle If-None-Match weak ETags examples server
#23916 opened May 30, 2026 by EZForever Contributor Loading…
1
loader: increase async upload staging buffer to 4 MiB
#23915 opened May 30, 2026 by cl0ckt0wer Loading…
mtmd, server: add "placeholder bitmap" for counting tokens , add */input_tokens API examples python python script changes server
#23913 opened May 30, 2026 by ngxson Contributor Loading…
3
ci : disable ccache for msvc windows release jobs devops improvements to build systems and github actions
#23911 opened May 30, 2026 by ggerganov Member Loading…
build: Add vulkan building script
#23908 opened May 30, 2026 by sapbotgit Loading…
2
cuda: reserve space for quantize kv-cache at startup ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23907 opened May 30, 2026 by am17an Contributor Loading…
12
lama-bench : fix default thread count evaluated at static init time examples
#23905 opened May 30, 2026 by Iamsujithd Loading…
1
2
fix: VMM pool cuMemSetAccess for ROCm gfx1151 APU ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23900 opened May 30, 2026 by ricred • Draft
1
vocab: add normalizer.lowercase support to WPM python python script changes
#23899 opened May 30, 2026 by o7si Contributor Loading…
5
llama-cli: fix model params not propagated examples
#23893 opened May 30, 2026 by therealkenc Loading…
1
docs: update HOWTO-add-model.md [no release] documentation Improvements or additions to documentation
#23883 opened May 29, 2026 by Xarbirus Contributor Loading…
2
metal: template GLU kernels to support f16/f32 Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#23882 opened May 29, 2026 by shrivasshankar Loading…
@ggerganov
ui: PWA support devops improvements to build systems and github actions examples script Script related server/ui server
#23871 opened May 29, 2026 by allozaur Contributor • Draft
1
32
ggml-hip: enable -ffast-math for HIP builds ggml changes relating to the ggml tensor library for machine learning
#23862 opened May 29, 2026 by a-huk Loading…
1 task done
3
llama: save more VRAM by reserving n_outputs == n_seqs when possible examples server
#23861 opened May 29, 2026 by am17an Contributor Loading…
2
chat: route LiquidAI LFM2.5 through specialized parser testing Everything test related
#23856 opened May 29, 2026 by mattngaw Loading…
1
3
agentic: question tool + shared plumbing examples python python script changes server/ui server
#23848 opened May 29, 2026 by LPFchan Loading…
5
nix: add nix-nodejs facilities to build Web UI devops improvements to build systems and github actions nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
#23846 opened May 29, 2026 by choener Loading…
1
2
ProTip! Add no:assignee to see everything that’s not assigned.