-
Notifications
You must be signed in to change notification settings - Fork 12.4k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
mtmd : Support jinja in libmtmd (Only for QwenVL and Qwen Omni)
examples
#14730
opened Jul 17, 2025 by
alielmorsy
Loading…
server: add prompt processing progress streaming for /completion endpoint #14685
examples
server
#14728
opened Jul 16, 2025 by
baonudesifeizhai
Loading…
nix: use optionalAttrs for improvements to build systems and github actions
nix
Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
env
mkDerivation attrset argument
devops
#14726
opened Jul 16, 2025 by
amozeo
Loading…
CUDA: set_rows + cpy.cu refactor
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#14712
opened Jul 16, 2025 by
am17an
Loading…
vulkan: Add logging for bf16 features to ggml_vk_print_gpu_info (#13274)
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#14707
opened Jul 16, 2025 by
Peter0x44
Loading…
Fix KleidiAI compilation errors with -DGGML_NATIVE=OFF (issue #14464)
ggml
changes relating to the ggml tensor library for machine learning
#14700
opened Jul 15, 2025 by
baonudesifeizhai
Loading…
Adding a simple-function-call example - hopefully not doing anything wrong
examples
#14682
opened Jul 14, 2025 by
klogdotwebsitenotdotcom
Loading…
kleidiai: add support for get_rows
ggml
changes relating to the ggml tensor library for machine learning
#14676
opened Jul 14, 2025 by
chaxu01
Loading…
bug fix: handle saving/loading null layers in recurrent memory
#14675
opened Jul 14, 2025 by
l3utterfly
Loading…
Add Pad Reflect 1D CUDA support
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#14659
opened Jul 13, 2025 by
YavorGIvanov
Loading…
Model: Add support for Ernie 4.5 MoE
python
python script changes
#14658
opened Jul 13, 2025 by
pwilkin
Loading…
webui : add a preset feature to the settings
examples
server
#14649
opened Jul 12, 2025 by
gabriellarson
Loading…
Add CUDA non-contiguous Unary Ops support
build
Compilation issues
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
testing
Everything test related
#14639
opened Jul 11, 2025 by
YavorGIvanov
Loading…
OpenCL: add changes relating to the ggml tensor library for machine learning
OpenCL
Issues specific to the OpenCL backend
mul_mat_f16_f32_image
kernel
ggml
#14635
opened Jul 11, 2025 by
rmatif
Loading…
Add EXAONE 4.0 model architecture
python
python script changes
#14630
opened Jul 11, 2025 by
lgai-exaone
Loading…
HIP: Enable Matrix cores for MMQ Kernels, Enable stream-K for CDNA 3
devops
improvements to build systems and github actions
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#14624
opened Jul 10, 2025 by
deepsek
Loading…
tool: add convertation of text/parquet to custom format
build
Compilation issues
examples
#14622
opened Jul 10, 2025 by
lexasub
Loading…
webui: Change Download function to download the full text of the conversation
examples
server
#14619
opened Jul 10, 2025 by
michaelmarziani
Loading…
metal : fuse add, mul
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
#14596
opened Jul 9, 2025 by
ggerganov
Loading…
4 tasks done
docker : add cann build pipline
Ascend NPU
issues specific to Ascend NPUs
devops
improvements to build systems and github actions
ggml
changes relating to the ggml tensor library for machine learning
#14591
opened Jul 9, 2025 by
diannaojiang
Loading…
metal : reuse graphs
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
demo
Demonstrate some concept or idea, not intended to be merged
ggml
changes relating to the ggml tensor library for machine learning
Previous Next
ProTip!
Filter pull requests by the default branch with base:master.