Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
582 Open 7,584 Closed
582 Open 7,584 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

batched-bench : add "separate text gen" mode examples
#17103 opened Nov 8, 2025 by ggerganov Loading…
metal : retain src and dst buffers during async ops Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#17101 opened Nov 8, 2025 by ggerganov Loading…
webui : add keyboard shortcut to toggle sidebar examples server
#17099 opened Nov 8, 2025 by danbev Loading…
Add Metal-4 Tensor API test harness for iOS examples
#17098 opened Nov 8, 2025 by ArjunDivecha Loading…
vulkan: fuse mul_mat_id + mul ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#17095 opened Nov 8, 2025 by jeffbolznv Loading…
1
CUDA: support F32 kernel type for CONV_TRANSPOSE_2D ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17094 opened Nov 8, 2025 by AgainstEntropy Loading…
add version to all shared object files Apple Metal https://en.wikipedia.org/wiki/Metal_(API) Ascend NPU issues specific to Ascend NPUs 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 SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language Vulkan Issues specific to the Vulkan backend
#17091 opened Nov 7, 2025 by furrysalamander Loading…
1
opencl: add fastdiv and use it in set_rows, ported from cuda ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#17090 opened Nov 7, 2025 by lhez • Draft
metal : enable tensor API for A19 Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#17087 opened Nov 7, 2025 by ggerganov Loading…
convert: (demo) repacking compressed_tensor format of kimi-k2 python python script changes
#17083 opened Nov 7, 2025 by ngxson • Draft
server : handle failures to restore host cache examples python python script changes server
#17078 opened Nov 7, 2025 by ggerganov Loading…
1
HIP: RDNA4 tensor core support for MMF ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17077 opened Nov 7, 2025 by zhang-hui-yulo • Draft
3
arg: add --cache-list argument to list cached models
#17073 opened Nov 7, 2025 by ngxson Loading…
4
[RFC] ggml: new backend for API Remoting Apple Metal https://en.wikipedia.org/wiki/Metal_(API) build Compilation issues ggml changes relating to the ggml tensor library for machine learning
#17072 opened Nov 7, 2025 by kpouget Loading…
convert : handle compressed-tensors quant method enhancement New feature or request python python script changes
#17069 opened Nov 7, 2025 by compilade Loading…
6 of 7 tasks
10
Fix NetBSD compilation error
#17068 opened Nov 7, 2025 by xinitrcn1 Loading…
Add ops needed for new hybrid models: SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17063 opened Nov 6, 2025 by pwilkin Loading…
23
cmake: add option to build and link BoringSSL build Compilation issues
#17062 opened Nov 6, 2025 by angt Loading…
5
[WIP] s390x ci: debug build issue devops improvements to build systems and github actions
#17053 opened Nov 6, 2025 by AlekseiNikiforovIBM Loading…
8
# Add Megrez-MoE Architecture Support ggml-org#16724 model Model specific
#17052 opened Nov 6, 2025 by tamarPal Loading…
8
cuda: extended MMF_ROWS_PER_BLOCK ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17051 opened Nov 6, 2025 by zhang-hui-yulo Loading…
3
fix : Dangling pointer for non-empty trigger words in lazy grammar construction
#17048 opened Nov 6, 2025 by marek-hradil Loading…
3
Add MoE dynamic routing with expert caching build Compilation issues documentation Improvements or additions to documentation examples
#17044 opened Nov 6, 2025 by jmangold23 • Draft
ggml-hexagon: fix test-backend-ops failures on specific binary ops ggml changes relating to the ggml tensor library for machine learning
#17042 opened Nov 6, 2025 by chraac • Draft
11
server/public_simplechat alternate web client ui with 0 setup builtin tool calling++, reasoning - refactored, SysDateTime, rename pdftext examples python python script changes server
#17038 opened Nov 5, 2025 by hanishkvc Loading…
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.