Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
628 Open 8,249 Closed
628 Open 8,249 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

common/grammar : replace problematic backtracking regex [\s\S]* testing Everything test related
#18342 opened Dec 24, 2025 by aldehir Loading…
1
ggml-cuda : fix INT_MAX overflow in cpy kernels (#18140) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18340 opened Dec 24, 2025 by Muhammad-Kamran-Khan Loading…
1
1
android: routine maintenance - Dec 2025 android Issues specific to Android examples
#18338 opened Dec 24, 2025 by naco-siren Loading…
[WIP]ggml-hexagon: improve leftover element calc at vec_dot_f16_f32 ggml changes relating to the ggml tensor library for machine learning
#18336 opened Dec 24, 2025 by chraac • Draft
1
webui: simple MCP (Model Context Protocol) support (stdio, tool calls) examples python python script changes server
#18334 opened Dec 24, 2025 by ochafik • Draft
2 of 8 tasks
mimo2: wire RMS eps + MoE bias + converter guard model Model specific python python script changes
#18333 opened Dec 24, 2025 by Aaryan-Kapoor Loading…
vulkan: Use BK=32 for coopmat2 mul_mat_id ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18332 opened Dec 23, 2025 by jeffbolznv Loading…
full modern bert support python python script changes
#18330 opened Dec 23, 2025 by ryan-mangeno Loading…
model: support MiMo-V2-Flash model Model specific python python script changes
#18328 opened Dec 23, 2025 by ngxson Loading…
1
1
vulkan: Support UPSCALE w/antialias ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#18327 opened Dec 23, 2025 by jeffbolznv Loading…
[WIP] model: add Trillion model model Model specific python python script changes
#18325 opened Dec 23, 2025 by HelloKS • Draft
3 tasks
server: (preset) add unsafe-allow-api-override examples server
#18322 opened Dec 23, 2025 by ngxson • Draft
12
Support Youtu-VL Model examples python python script changes
#18315 opened Dec 23, 2025 by f291400 Loading…
22
Add metal count equal op Apple Metal https://en.wikipedia.org/wiki/Metal_(API) documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning
#18314 opened Dec 23, 2025 by gatbontonpc Loading…
4
utils: beging using log.h in tokenize.cpp examples
#18307 opened Dec 22, 2025 by syedshazli Loading…
1
vulkan: handle rope with large number of rows ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#18306 opened Dec 22, 2025 by jeffbolznv Loading…
1
vulkan: fix command buffer corruption in ggml_backend_vk_event_wait ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18302 opened Dec 22, 2025 by jeffbolznv Loading…
1
Webui/prompt processing progress examples server
#18300 opened Dec 22, 2025 by ServeurpersoCom Loading…
1
6
vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#18295 opened Dec 22, 2025 by jeffbolznv Loading…
1
server: implement --shutdown-timeout examples server
#18292 opened Dec 22, 2025 by ngxson Loading…
1
9
eval-callback : add support for saving logits examples
#18281 opened Dec 22, 2025 by danbev Loading…
6
Cmdline arg -to changes http read timeout from current 600sec default examples server
#18279 opened Dec 22, 2025 by wbtek Loading…
10
tools : use common_log_pause to fix fit-params output race examples
#18276 opened Dec 22, 2025 by Aadeshveer Loading…
1
2
KYLIN: fix compile error for cuda backend ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18275 opened Dec 22, 2025 by lizhenneng Loading…
1
llama: fix magic number of 999 for GPU layers
#18266 opened Dec 21, 2025 by JohannesGaessler Loading…
1
3
ProTip! Type g i on any issue or pull request to go back to the issue listing page.