Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
732 Open 9,097 Closed
732 Open 9,097 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

scripts: ini_to_opencode.py python python script changes script Script related
#19938 opened Feb 26, 2026 by am17an Loading…
2
fix dots.ocr: correct RoPE sections and FFN tensor mapping examples python python script changes
#19936 opened Feb 26, 2026 by anthony-maio Loading…
1 of 2 tasks
1
common : update completion executables list [no ci]
#19934 opened Feb 26, 2026 by danbev Loading…
llama: disable repack by default devops improvements to build systems and github actions
#19932 opened Feb 26, 2026 by am17an Loading…
6
tool parser: add GigaChatV3/3.1 models support in PEG format testing Everything test related
#19931 opened Feb 26, 2026 by Mishusha Loading…
metal: add CONV_3D Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#19927 opened Feb 26, 2026 by Ra5hidIslam Loading…
server : support multiple model aliases via comma-separated --alias examples python python script changes server
#19926 opened Feb 26, 2026 by ServeurpersoCom Loading…
1
8
ggml : fix AMX and add batched support ggml changes relating to the ggml tensor library for machine learning
#19925 opened Feb 26, 2026 by angt Loading…
2
ggml-zendnn : update code for latest ZenDNN API documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning
#19923 opened Feb 26, 2026 by z-vishal Loading…
1
llama/ggml: multi-GPU pipeline parallelism (xdev host staging) + faster model loading ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#19922 opened Feb 26, 2026 by mxxm-t Loading…
1
[SYCL] Replace the magic nunber 768 by max work group size to support iGPU ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#19920 opened Feb 26, 2026 by arthw Loading…
ggml-cuda: add mem check for fusion ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#19916 opened Feb 26, 2026 by am17an • Draft
vendors: update miniaudio library to 0.11.24 python python script changes script Script related
#19914 opened Feb 26, 2026 by data-man Loading…
test-backend-ops: allow loading tests from JSON and parsing model operators into JSON examples testing Everything test related
#19896 opened Feb 25, 2026 by 0cc4m Loading…
Mirroring /v1/responses to /responses examples server
#19873 opened Feb 25, 2026 by samikama Loading…
[ggml-quants] Add memsets and other fixes for IQ quants ggml changes relating to the ggml tensor library for machine learning
#19861 opened Feb 24, 2026 by bartowski1182 Loading…
15
server : add default-model preset and fallback logic examples server
#19855 opened Feb 24, 2026 by mikhail-shevtsov-wiregate Loading…
ggml-webgpu: Support non-contiguous src0 and overlapping src0/src1 in binary ops ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#19850 opened Feb 24, 2026 by yomaytk Loading…
2
Add chat truncation [WIP] examples python python script changes server testing Everything test related
#19841 opened Feb 23, 2026 by ltoniazzi • Draft
6 tasks
26
opencl: add optimized q4_1 mm kernel for adreno ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#19840 opened Feb 23, 2026 by shaofeiqi • Draft
sampling : support multiple outputs per sequence examples server testing Everything test related
#19833 opened Feb 23, 2026 by danbev • Draft
2 tasks
Add Aya 101 multi-lingual translation support to llama.cpp examples python python script changes server
#19832 opened Feb 23, 2026 by Acceldium Loading…
5
common : refactor cache to use hierarchical directory layout
#19828 opened Feb 23, 2026 by angt Loading…
1
Kimi Linear block implementation model Model specific
#19827 opened Feb 23, 2026 by ymcki Loading…
7
implemented max pooling for embeddings examples python python script changes server
#19812 opened Feb 22, 2026 by lorenzocesconetto Loading…
ProTip! What’s not been updated in a month: updated:<2026-01-26.