Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,190 Open 11,987 Closed
1,190 Open 11,987 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

Deepseek V4: split-mode tensor ggml changes relating to the ggml tensor library for machine learning
#25860 opened Jul 18, 2026 by S3kundes • Draft
2
sycl: parallelize the non-contiguous concat kernel ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#25852 opened Jul 18, 2026 by Titaniumtown Contributor Loading…
vulkan: add TQ2_0 (ternary) support ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#25850 opened Jul 18, 2026 by michaeltrabalka-tech Loading…
1 task done
2
server: server tools - get_datetime in UTC ISO format server
#25848 opened Jul 17, 2026 by radupotop Loading…
webgpu : add CONV_2D_DW (depthwise conv2d) kernel documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning WebGPU
#25847 opened Jul 17, 2026 by m1el Loading…
ui: Add a "Default" option for the reasoning selector server/ui
#25846 opened Jul 17, 2026 by ServeurpersoCom Contributor Loading…
1
mtmd : fix llava CLS token ordering (#25814) mtmd Related to multimodal functionality (video/image/audio)
#25844 opened Jul 17, 2026 by waleedabujaish Loading…
1 task done
1
docs: warn when --ubatch-size is too small in --embeddings mode documentation Improvements or additions to documentation server
#25841 opened Jul 17, 2026 by chinmaykamjith001 Loading…
1
ggml-cuda: add optional DP2A fallback for DP4A CUDA Related to the CUDA backend documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning
#25834 opened Jul 17, 2026 by sj0618 Loading…
1
1
ggml : adjust logic for offloading ops to weight's backend ggml changes relating to the ggml tensor library for machine learning model Model specific
#25832 opened Jul 17, 2026 by ggerganov Member Loading…
1
3
gguf : make gguf_writer_base destructor virtual ggml changes relating to the ggml tensor library for machine learning
#25831 opened Jul 17, 2026 by yymin1022 Loading…
2
server : add missing task parameters(adaptive_target, adaptive_decay) in generation_settings server
#25830 opened Jul 17, 2026 by tekinertekin Loading…
1
dflash: rotate injected K/V cache when using K/V quantization model Model specific
#25823 opened Jul 17, 2026 by ruixiang63 Member Loading…
1
4
llama : add n_layer_all upper bound check to prevent OOB write documentation Improvements or additions to documentation
#25821 opened Jul 17, 2026 by oakkaya Loading…
1
contrib: add contributing guidelines for new backends documentation Improvements or additions to documentation
#25820 opened Jul 17, 2026 by taronaeo Member Loading…
server : add stuck-loop escape for ngram-mod (WIP) server
#25819 opened Jul 17, 2026 by yychyo Contributor • Draft
server : remote speculative decoding via ethernet server
#25818 opened Jul 17, 2026 by xkmire Loading…
server : add trace logs for slot prefix similarity computation server
#25816 opened Jul 17, 2026 by ggerganov Member • Draft
ui: Sidebar Conversations Bulk Action + Improved Settings logic/UI server/ui
#25815 opened Jul 17, 2026 by allozaur Contributor Loading…
25
server : add realtime inference stats to /slots endpoint documentation Improvements or additions to documentation server
#25813 opened Jul 17, 2026 by zhangrunda Contributor Loading…
1 task done
llama-context: don't disable fusion when layer is offloaded
#25806 opened Jul 17, 2026 by am17an Contributor Loading…
1
4
docs: add gpt-oss guide documentation Improvements or additions to documentation
#25799 opened Jul 17, 2026 by azeez-1904 • Draft
2
docs: add embeddings tutorial documentation Improvements or additions to documentation
#25798 opened Jul 17, 2026 by azeez-1904 Loading…
2
Add GGML_BACKEND_DL_IMPL invocation for OpenVINO backend ggml changes relating to the ggml tensor library for machine learning OpenVINO
#25795 opened Jul 17, 2026 by seijikun Loading…
1
1
spec: add eagle3-v3 support for gpt-oss conversion model Model specific
#25794 opened Jul 16, 2026 by ruixiang63 Member Loading…
@ggerganov
ProTip! no:milestone will show everything without a milestone.