Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
624 Open 8,105 Closed
624 Open 8,105 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

vulkan: Implement set_tensor_async and the event interfaces ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18047 opened Dec 15, 2025 by jeffbolznv Loading…
chat-parser: handle whitespace around JSON in tool call parsing testing Everything test related
#18044 opened Dec 15, 2025 by ochafik • Draft
convert : keep file part order from model index python python script changes
#18043 opened Dec 14, 2025 by CISC Loading…
model: support GLM4V vision encoder examples model Model specific python python script changes
#18042 opened Dec 14, 2025 by ngxson • Draft
[Speculative decoding] feat: add EAGLE3 speculative decoding support examples ggml changes relating to the ggml tensor library for machine learning model Model specific python python script changes
#18039 opened Dec 14, 2025 by ichbinhandsome • Draft
Extend run-org-model.py examples python python script changes
#18034 opened Dec 14, 2025 by pwilkin Loading…
vulkan: use 4 rows for scalar FA large tile size ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18033 opened Dec 14, 2025 by jeffbolznv Loading…
model: add KORMo model python python script changes
#18032 opened Dec 14, 2025 by HelloKS Loading…
9
Vulkan: some improvement on mul_mat_iq2_xs ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18031 opened Dec 14, 2025 by lovedheart Loading…
1
feat: add --moe-n-expert flag for MoE expert count override
#18029 opened Dec 14, 2025 by pestopoppa Loading…
4 tasks done
5
Webui/server config defaults examples server
#18028 opened Dec 14, 2025 by ServeurpersoCom Loading…
1
13
ggml-blas: refactor BLAS backend ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#18027 opened Dec 14, 2025 by taronaeo • Draft
1
added note for old Intel hardware pre sycl documentation Improvements or additions to documentation SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#18017 opened Dec 14, 2025 by alosslessdev Loading…
1
on opencl added note for pre SYCL Intel hardware documentation Improvements or additions to documentation OpenCL Issues specific to the OpenCL backend
#18016 opened Dec 14, 2025 by alosslessdev Loading…
1
Add message for pre-RDNA AMD GPU support via opencl documentation Improvements or additions to documentation
#18015 opened Dec 14, 2025 by alosslessdev Loading…
1
Async DirectIO model loading on Linux
#18012 opened Dec 13, 2025 by JTischbein Loading…
5
webui: fix chat screen shadow width examples server
#18010 opened Dec 13, 2025 by polydecay Loading…
1
CLI: fixed adding cli and completion into docker containers, improved docs devops improvements to build systems and github actions documentation Improvements or additions to documentation
#18003 opened Dec 13, 2025 by andrew-aladev Loading…
11
Clarify that steps also apply to linux documentation Improvements or additions to documentation
#18002 opened Dec 13, 2025 by alosslessdev Loading…
server: add /v1/metrics endpoint examples server
#18001 opened Dec 13, 2025 by Kritavya Loading…
4
arg: clarify auto kvu/np being set on server examples server
#17997 opened Dec 13, 2025 by ngxson Loading…
1
Optimization: Qwen3 next autoregressive pass model Model specific
#17996 opened Dec 13, 2025 by pwilkin Loading…
23
CLI: fixed dead links to tools/main for cli and completion, fixed code owners documentation Improvements or additions to documentation examples
#17993 opened Dec 13, 2025 by andrew-aladev Loading…
1
HIP: Refactor mma for RDNA and CDNA ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17990 opened Dec 13, 2025 by zhang-hui-yulo • Draft
1 task
8
kv-cache: Fix state restore fragmented cache testing Everything test related
#17982 opened Dec 13, 2025 by ssweens Loading…
1
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.