Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
540 Open 6,955 Closed
540 Open 6,955 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

Add LLaDA-7b-MoE diffusion model
#16003 opened Sep 15, 2025 by am17an Loading…
examples : support encoder-decoder models in the simple example examples
#16002 opened Sep 15, 2025 by DamonFool Loading…
--numa mirror: mirror model weights to every Numa node in the system Apple Metal https://en.wikipedia.org/wiki/Metal_(API) Ascend NPU issues specific to Ascend NPUs devops improvements to build systems and github actions examples ggml changes relating to the ggml tensor library for machine learning IBM zDNN issues specific to IBM zDNN Accelerator Nvidia GPU Issues specific to Nvidia GPUs OpenCL Issues specific to the OpenCL backend python python script changes SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#16000 opened Sep 15, 2025 by dbsanfte • Draft
1
server: added support for systemd socket activation and readiness reporting build Compilation issues examples server
#15998 opened Sep 14, 2025 by pvaret Loading…
1
docker : enable rocWMMA in ROCm images, add gfx1151 devops improvements to build systems and github actions
#15997 opened Sep 14, 2025 by slaren Loading…
2
metal : refactor + optimize v2 Apple Metal https://en.wikipedia.org/wiki/Metal_(API) devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning
#15995 opened Sep 14, 2025 by ggerganov • Draft
2 of 5 tasks
vulkan : shader development improvements ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15993 opened Sep 14, 2025 by Acly Loading…
2
releases : switch to rocWMMA develop branch, add gfx1151 devops improvements to build systems and github actions
#15992 opened Sep 14, 2025 by slaren Loading…
2
SYCL: Add COUNT_EQUAL operator support documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related
#15991 opened Sep 14, 2025 by yael-works Loading…
3
ggml: add FLOOR unary op (CPU + SYCL) ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related
#15989 opened Sep 14, 2025 by safranowith Loading…
2
llama-run: Fix model download on Windows examples
#15988 opened Sep 14, 2025 by npopov-vst Loading…
7
metal : use virtual GPU address for private buffers Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#15985 opened Sep 14, 2025 by ggerganov • Draft
CUDA: fix FA occupancy, optimize tile kernel ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#15982 opened Sep 14, 2025 by JohannesGaessler Loading…
SYCL: Add ARANGE operator with GPU kernel, tests, and documentation documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related
#15978 opened Sep 14, 2025 by GittyBurstein Loading…
vulkan: automatically remove unsupported devices ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15976 opened Sep 14, 2025 by netrunnereve Loading…
4
cli: allow layer groups in --n-cpu-moe
#15975 opened Sep 14, 2025 by lksj92hs Loading…
2
Add resumable downloads for llama-server model loading
#15963 opened Sep 13, 2025 by ericcurtin Loading…
15
CUDA: Optimize PAD_REFLECT_1D ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#15957 opened Sep 13, 2025 by bugparty Loading…
13
CUDA: fix im2col_3d to respect non-contiguous inputs (views) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#15956 opened Sep 13, 2025 by jakekarnes42 Loading…
2
ggml-cpu: optimize the ggml NORM operation ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#15953 opened Sep 12, 2025 by duduta Loading…
3
llama-bench: add --n-cpu-moe support examples
#15952 opened Sep 12, 2025 by jacekpoplawski Loading…
@pwilkin
11
opencl: fix concat crash on win arm64 with Adreno ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#15944 opened Sep 12, 2025 by lhez Loading…
ci : update macos-latest* jobs to use macos-latest devops improvements to build systems and github actions
#15938 opened Sep 11, 2025 by danbev Loading…
4
CANN: Fix ggml_cann_set_device to avoid redundant device switches Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#15935 opened Sep 11, 2025 by noemotiovon Loading…
2
ggml : fix padding in timestep embedding kernels Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs OpenCL Issues specific to the OpenCL backend SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language Vulkan Issues specific to the Vulkan backend
#15932 opened Sep 11, 2025 by danbev Loading…
4
ProTip! Mix and match filters to narrow down what you’re looking for.