Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
917 Open 10,225 Closed
917 Open 10,225 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

metal : print GPU description
#22318 opened Apr 24, 2026 by ggerganov Member Loading…
ggml-cpu: cmake: append xsmtvdotii march for SpacemiT IME
#22317 opened Apr 24, 2026 by qiurui144 Loading…
gitignore : add .pi + personal SYSTEM.md devops improvements to build systems and github actions
#22316 opened Apr 24, 2026 by ggerganov Member Loading…
common : fix jinja warnings with clang 21 jinja parser Issues related to the jinja parser merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge.
#22313 opened Apr 24, 2026 by angt Member Loading…
2
hexagon: use DIRID 13 in libggml-htp.inf for modern InfVerif ggml changes relating to the ggml tensor library for machine learning Hexagon
#22306 opened Apr 24, 2026 by mengshengwu Contributor Loading…
3 tasks done
CI Snapdragon: Switch ubuntu-latest to ubuntu-slim runner devops improvements to build systems and github actions
#22303 opened Apr 23, 2026 by shreyajn Contributor Loading…
5
parser: fix structured output bug examples python python script changes script Script related server
#22302 opened Apr 23, 2026 by pwilkin Member Loading…
1
3
Adreno optimization for MoE - MxFP4 ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#22301 opened Apr 23, 2026 by shawngu-quic Contributor Loading…
2
internal AllReduce kernel for CUDA provider examples ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22299 opened Apr 23, 2026 by scutler-nv • Draft
CUDA: reduce MMQ stream-k overhead ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22298 opened Apr 23, 2026 by JohannesGaessler Contributor Loading…
8
CUDA: add POOL_1D ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22297 opened Apr 23, 2026 by LeoYangXY Loading…
4
ggml : skip already registered backends and devices ggml changes relating to the ggml tensor library for machine learning
#22296 opened Apr 23, 2026 by angt Member Loading…
1
ggml-cpu : disable tiled matmul on AIX to fix page boundary segfault ggml changes relating to the ggml tensor library for machine learning
#22293 opened Apr 23, 2026 by shalinib-ibm Contributor Loading…
4
[SYCL] Optimize Q4_0 mul_mat for Arc770, add scripts documentation Improvements or additions to documentation examples ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22291 opened Apr 23, 2026 by arthw Contributor Loading…
5
common : only load backends when required ggml changes relating to the ggml tensor library for machine learning
#22290 opened Apr 23, 2026 by angt Member Loading…
3
ggml-cuda: add flash-attn support for DKQ=320/DV=256 with ncols2=32 (… ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#22286 opened Apr 23, 2026 by lnigam Loading…
4
server: router fix model unload reload deadlock examples python python script changes server
#22284 opened Apr 23, 2026 by 0cc4m Contributor • Draft
Update CMakeLists.txt ggml changes relating to the ggml tensor library for machine learning need more info The OP should provide more details about the issue
#22282 opened Apr 23, 2026 by fsavanur Loading…
Feature/add -ms option for modelscope
#22279 opened Apr 23, 2026 by yrk111222 Loading…
1
llama : integer type consistency in llama.h #4574
#22277 opened Apr 23, 2026 by Vladimirhoa Loading…
common: Changed to leak logger singleton to prevent hanging on Windows
#22273 opened Apr 23, 2026 by rillomas Contributor Loading…
3
opencl: add iq4_nl support ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#22272 opened Apr 23, 2026 by lhez Contributor • Draft
readme : add D bindings (llama-cpp-d)
#22270 opened Apr 23, 2026 by AMDphreak Loading…
webui: add option for LLM title generation examples server/webui server
#22265 opened Apr 22, 2026 by smugman-dot Loading…
1
common: fix macOS cache path segfault when HOME is unset
#22263 opened Apr 22, 2026 by Geramy Loading…
1
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.