Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
671 Open 8,734 Closed
671 Open 8,734 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

nix: fix nix develop .#python-scripts devops improvements to build systems and github actions nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
#19218 opened Jan 30, 2026 by teto Loading…
ggml-cpu: split across kv for faster TG ggml changes relating to the ggml tensor library for machine learning
#19209 opened Jan 30, 2026 by am17an Loading…
2
ggml-virtgpu: make the code thread safe ggml changes relating to the ggml tensor library for machine learning python python script changes
#19204 opened Jan 30, 2026 by kpouget Loading…
7
ggml-cpu: optimize q4_0_q8_0 scales using Zvfhmin ggml changes relating to the ggml tensor library for machine learning
#19196 opened Jan 30, 2026 by ixgbe Loading…
Remove pipeline cache mutexes ggml changes relating to the ggml tensor library for machine learning
#19195 opened Jan 30, 2026 by nikhilJain17 Loading…
1
Refactor vk_semaphore to be a shared_ptr object ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19193 opened Jan 30, 2026 by sredman Loading…
5
Bump cmake max version (needed for Windows on Snapdragon builds) build Compilation issues documentation Improvements or additions to documentation
#19188 opened Jan 29, 2026 by max-krasnyansky Loading…
2
[RFC] implementing Expected Attention in llama.cpp? examples
#19183 opened Jan 29, 2026 by ddh0 • Draft
2
model: support Longcat-Flash (help wanted) help wanted Needs help from the community model Model specific python python script changes
#19182 opened Jan 29, 2026 by ngxson • Draft
6
Hybrid model loading with DirectIO and MMAP
#19180 opened Jan 29, 2026 by JTischbein • Draft
ggml-backend: fix async set/get fallback sync ggml changes relating to the ggml tensor library for machine learning
#19179 opened Jan 29, 2026 by JohannesGaessler Loading…
1
ggml: optimize ggml_vec_dot_mxfp4_q8_0 dot product on ARM SVE ggml changes relating to the ggml tensor library for machine learning
#19171 opened Jan 29, 2026 by jiangshhh Loading…
3
Add Kimi-K2.5 support python python script changes
#19170 opened Jan 29, 2026 by AesSedai • Draft
3
model : support LongCat-Flash-Lite (ngram embeddings) model Model specific
#19167 opened Jan 28, 2026 by ngxson • Draft
9
Update server-models.cpp examples server
#19166 opened Jan 28, 2026 by NNEngine Loading…
common : convert string contents to arrays if template requires typed content jinja parser Issues related to the jinja parser
#19156 opened Jan 28, 2026 by ownia Loading…
6
common: fix 32-bit overflow for avoiding year 2038 problem
#19148 opened Jan 27, 2026 by GermanAizek Loading…
[WIP]ggml-hexagon: flash-attn opt - part2 ggml changes relating to the ggml tensor library for machine learning
#19141 opened Jan 27, 2026 by chraac • Draft
3
llama: Add option to merge gate and exp weights model Model specific python python script changes
#19139 opened Jan 27, 2026 by am17an Loading…
21
ggml: aarch64: Implement SVE in Gemm q4_k 8x8 q8_k Kernel ggml changes relating to the ggml tensor library for machine learning
#19132 opened Jan 27, 2026 by abhijain1204fujitsu Loading…
9
Unified Delta Net model Model specific python python script changes
#19125 opened Jan 27, 2026 by ymcki Loading…
1
ggml-cpu: add RVV repack GEMM and GEMV for quantization types ggml changes relating to the ggml tensor library for machine learning
#19121 opened Jan 26, 2026 by taimur-10x Loading…
server: print actual model name in 'model not found" error examples server
#19117 opened Jan 26, 2026 by teto Loading…
4
common : add specific warning for multiple -m options
#19113 opened Jan 26, 2026 by danbev Loading…
6
Check if ctx or model is null before calling sampler examples
#19101 opened Jan 26, 2026 by gagankonana Loading…
1
4
ProTip! Updated in the last three days: updated:>2026-01-27.