Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
555 Open 7,398 Closed
555 Open 7,398 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

llama: fix leaked buffers for mmap + split files
#16765 opened Oct 25, 2025 by JohannesGaessler Loading…
1
model : add LightOnOCR-1B model examples python python script changes
#16764 opened Oct 24, 2025 by ngxson Loading…
Add LFM2 tool handling testing Everything test related
#16763 opened Oct 24, 2025 by ykhrustalev Loading…
convert: Handle mmproj model output filename properly python python script changes
#16760 opened Oct 24, 2025 by Galunid Loading…
3
webui: add HTML/JS preview support to MarkdownContent with sandboxed iframe examples server
#16757 opened Oct 24, 2025 by ServeurpersoCom Loading…
7
qwen3-coder tool call parser testing Everything test related
#16755 opened Oct 24, 2025 by marceldev89 Loading…
1
3
rpc: use XXHash64 instead of FNV-1a for hashing tensors ggml changes relating to the ggml tensor library for machine learning
#16753 opened Oct 24, 2025 by jukofyork • Draft
1
cann: improve device ID handling and aclnnArange checks Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#16752 opened Oct 24, 2025 by noemotiovon Loading…
4
convert: clean Gemma vision/audio chat template markers python python script changes
#16749 opened Oct 24, 2025 by pockers21 • Draft
1
llama : disable pipeline parallelism if compute buffer allocation fails
#16748 opened Oct 23, 2025 by slaren Loading…
llama: consistent ctx <-> buf order for KV cache ggml changes relating to the ggml tensor library for machine learning
#16746 opened Oct 23, 2025 by JohannesGaessler Loading…
1
Qwen vl bounding box and overall vision fix examples
#16745 opened Oct 23, 2025 by FMayran Loading…
6
ggml: fix cuda kernel launch configuration for k_compute_batched_ptrs to support large batch ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#16744 opened Oct 23, 2025 by leejet Loading…
5
get_rows & dequantize function implementation for repacked weights of type q6_K (q6_Kx8) ggml changes relating to the ggml tensor library for machine learning
#16743 opened Oct 23, 2025 by swetha097 Loading…
ggml-cpu: arm64: q4_K repack gemm and gemv implementations ggml changes relating to the ggml tensor library for machine learning
#16739 opened Oct 23, 2025 by Alcpz Loading…
server : support unified cache across slots examples python python script changes server
#16736 opened Oct 23, 2025 by ggerganov • Draft
1 of 4 tasks
4
sycl: add REPEAT_BACK operation support ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#16734 opened Oct 23, 2025 by shani-f Loading…
1
llama-server : Reduce log level of a debug message leaking prompt contents examples server
#16727 opened Oct 22, 2025 by l-austenfeld Loading…
CUDA: General GEMV fusion ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes testing Everything test related
#16715 opened Oct 22, 2025 by am17an Loading…
15
CUDA: support for weight clamp in top-k norm ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#16702 opened Oct 21, 2025 by am17an Loading…
14
model : add PaddleOCR examples python python script changes
#16701 opened Oct 21, 2025 by ngxson • Draft
1
ggml : fix interpolate with align-corners and ne=1 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs OpenCL Issues specific to the OpenCL backend testing Everything test related Vulkan Issues specific to the Vulkan backend
#16700 opened Oct 21, 2025 by Acly Loading…
2
fix[readme]: Update docs/build.md to match the new GPU_TARGETS documentation Improvements or additions to documentation
#16698 opened Oct 21, 2025 by catan2001 Loading…
llama-context: fix build fails with -Werror=missing-braces
#16692 opened Oct 21, 2025 by otegami Loading…
convert : enable expert group selection for all models with it python python script changes
#16691 opened Oct 20, 2025 by CISC Loading…
2
ProTip! Filter pull requests by the default branch with base:master.