Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
461 Open 5,859 Closed
461 Open 5,859 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

CUDA: fix typo in FlashAttention code ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13926 opened May 30, 2025 by JohannesGaessler Loading…
llama : deprecate explicit kv_self defrag/update calls examples
#13921 opened May 30, 2025 by ggerganov Loading…
kv-cache : split implementation in separate sources
#13920 opened May 30, 2025 by ggerganov Loading…
mtmd : drop _shared from libmtmd name, merge helpers into libmtmd (⚠️ breaking change) examples server
#13917 opened May 30, 2025 by ngxson Loading…
4
[CANN]Support Acl Graph ggml changes relating to the ggml tensor library for machine learning
#13915 opened May 30, 2025 by noemotiovon • Draft
[Ascend NPU] Enable labeler devops improvements to build systems and github actions
#13914 opened May 30, 2025 by shink Loading…
remove WIP since PR has been merged documentation Improvements or additions to documentation
#13912 opened May 30, 2025 by pepijndevos Loading…
convert: add eagle2 draft arch python python script changes
#13908 opened May 30, 2025 by pockers21 Loading…
2
Hybrid recurrent cache
#13904 opened May 29, 2025 by gabe-l-hart • Draft
1 task
2
ci(intel): venv for python & pip installation for intel docker devops improvements to build systems and github actions
#13898 opened May 29, 2025 by Thammachart Loading…
CUDA: add a prop in ggml_cuda_device_infor for distinguish iGPU or dGPU in cuda (#13856) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13895 opened May 29, 2025 by Yangxiaoz Loading…
18
Need to undefine "hz" on AIX examples
#13894 opened May 29, 2025 by mehendarkarprajwal Loading…
ggml-cpu : split arch-specific implementations ggml changes relating to the ggml tensor library for machine learning
#13892 opened May 29, 2025 by xctan • Draft
1
[WIP] model: add new model minimax-text-01 python python script changes
#13889 opened May 29, 2025 by qscqesze • Draft
musa: extract ggml_cuda_mul_mat_batched_cublas_gemm_batched_ex ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13887 opened May 29, 2025 by yeahdongcn Loading…
3 tasks done
4
sycl: Add reorder to Q6_K mmvq implementation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13885 opened May 29, 2025 by s-Nick Loading…
finetune.cpp command-line arg build Compilation issues examples ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#13873 opened May 28, 2025 by graehl Loading…
18
docs : add "Quick start" section for new users documentation Improvements or additions to documentation
#13862 opened May 28, 2025 by ngxson Loading…
4
tests : add test-tokenizers-remote testing Everything test related
#13846 opened May 28, 2025 by CISC Loading…
12
llama : auto-batch examples server
#13845 opened May 28, 2025 by ggerganov Loading…
1 task
3
musa: enable fp16 mma (all) and cublas on qy2 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#13842 opened May 28, 2025 by yeahdongcn Loading…
3 tasks done
9
OpenCL: Add concat, tsembd, upscale, tanh, pad and repeat ggml changes relating to the ggml tensor library for machine learning
#13840 opened May 28, 2025 by rmatif Loading…
9
kv-cache : avoid modifying recurrent cells when setting inputs
#13834 opened May 27, 2025 by compilade Loading…
6
llama : use n_swa + n_ubatch cells for SWA cache examples server
#13833 opened May 27, 2025 by ggerganov Loading…
3 tasks done
3
convert: add support for Japanese Bert model python python script changes
#13830 opened May 27, 2025 by huydt84 Loading…
16
ProTip! no:milestone will show everything without a milestone.