Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
571 Open 7,491 Closed
571 Open 7,491 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

server/public_simplechat - pdf2text toolcall initial go (wip) examples python python script changes server
#16929 opened Nov 1, 2025 by hanishkvc Loading…
hparams : add n_embd_full to support extended embed examples
#16928 opened Nov 1, 2025 by CISC Loading…
1
2
Add initial devcontainer configuration
#16926 opened Nov 1, 2025 by FXJEFE Loading…
Add e2e tests for embedding raw flag devops improvements to build systems and github actions examples python python script changes
#16923 opened Nov 1, 2025 by SamMalayek Loading…
1
disable D_TYPE same as A_TYPE cast for rope shaders ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16922 opened Nov 1, 2025 by futz12 Loading…
1
2
mtmd: add --image-min/max-tokens examples server
#16921 opened Nov 1, 2025 by ngxson Loading…
docs: remove llama_sampler_accept reference in sampling sample usage
#16920 opened Nov 1, 2025 by alundb Loading…
1
vulkan: Fix GGML_VULKAN_CHECK_RESULTS to better handle fusion ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16919 opened Nov 1, 2025 by jeffbolznv Loading…
devops: fix failing s390x docker build devops improvements to build systems and github actions documentation Improvements or additions to documentation
#16918 opened Nov 1, 2025 by taronaeo Loading…
CUDA: add FLOOR, CEIL, ROUND, TRUNC unary ops ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16917 opened Nov 1, 2025 by mnehete32 Loading…
1
add TheRock HIP backend build instructions documentation Improvements or additions to documentation
#16915 opened Nov 1, 2025 by lihaofd Loading…
1
opencl: support imrope ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#16914 opened Nov 1, 2025 by lhez • Draft
ggml-hexagon: replace sprintf with snprintf in ops-utils.h ggml changes relating to the ggml tensor library for machine learning
#16913 opened Nov 1, 2025 by chraac Loading…
1
Support video in mtmd and server examples server
#16910 opened Nov 1, 2025 by MrAMS • Draft
23
Vulkan: improve mul_mat_vec_iq1_m ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16907 opened Nov 1, 2025 by lovedheart Loading…
1
model: add Janus Pro for image understanding examples python python script changes
#16906 opened Oct 31, 2025 by ravenouse Loading…
8
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16900 opened Oct 31, 2025 by 0cc4m Loading…
4
rpc: join small packets in send_msg and recv_msg ggml changes relating to the ggml tensor library for machine learning
#16892 opened Oct 31, 2025 by jukofyork • Draft
2
ggml-cpu : bicubic interpolation ggml changes relating to the ggml tensor library for machine learning
#16891 opened Oct 31, 2025 by Acly Loading…
ggml-cpu : optimize RVV q2_k and q3_k kernels ggml changes relating to the ggml tensor library for machine learning
#16887 opened Oct 31, 2025 by xctan Loading…
1
cann: update cross_entropy_loss op support Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#16886 opened Oct 31, 2025 by TecJesh Loading…
CUDA: fuse rope + set_rows ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16884 opened Oct 31, 2025 by am17an Loading…
10
Disable NUMA-specific chunking for high-core-count HPC systems ggml changes relating to the ggml tensor library for machine learning
#16882 opened Oct 31, 2025 by rageshh-fj Loading…
1
server: add support for local image path loading for server examples server
#16874 opened Oct 30, 2025 by cchadowitz Loading…
1
SYCL: optimized repeat_back kernel (3× fewer asm instructions, 2× faster)Feature/sycl repeat back opt ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#16869 opened Oct 30, 2025 by shani-f Loading…
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.