-
Notifications
You must be signed in to change notification settings - Fork 13.7k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
vulkan: skip all-negative-inf blocks in FA
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17186
opened Nov 12, 2025 by
jeffbolznv
Loading…
ggml webgpu: add support for emscripten builds
build
Compilation issues
devops
improvements to build systems and github actions
ggml
changes relating to the ggml tensor library for machine learning
script
Script related
testing
Everything test related
#17184
opened Nov 12, 2025 by
reeselevine
Loading…
vulkan: add LOG operation support for F32 and F16
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17183
opened Nov 12, 2025 by
zayac
Loading…
opencl: add kernel to handle mat mul in attention to improve encoding speed
ggml
changes relating to the ggml tensor library for machine learning
OpenCL
Issues specific to the OpenCL backend
#17181
opened Nov 11, 2025 by
shaofeiqi
Loading…
metal: accelerated conv2d
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
#17175
opened Nov 11, 2025 by
bghira
Loading…
server: (refactor) implement generator-based API for task results
examples
server
#17174
opened Nov 11, 2025 by
ngxson
Loading…
cmake : fix ARM feature verification
ggml
changes relating to the ggml tensor library for machine learning
#17170
opened Nov 11, 2025 by
angt
Loading…
server: move res_error/res_ok to static function
examples
server
#17167
opened Nov 11, 2025 by
ngxson
Loading…
vulkan: change graph_compute to be async and enable get_tensor_async
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17158
opened Nov 10, 2025 by
jeffbolznv
Loading…
HIP: WMMA-MMQ kernels for RDNA 4
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#17156
opened Nov 10, 2025 by
jiachengjason
Loading…
llama.android : Rewrite Android binding
android
Issues specific to Android
documentation
Improvements or additions to documentation
examples
ggml
changes relating to the ggml tensor library for machine learning
#17152
opened Nov 10, 2025 by
hanyin-arm
Loading…
vulkan: add q2_K implementation in mul_mmq with ACC_TYPE_VEC2
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17147
opened Nov 10, 2025 by
SavicStefan
Loading…
metal : make the FA extra sizes consistent
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
#17143
opened Nov 10, 2025 by
ggerganov
Loading…
Add complete Megrez-MoE support: GGUF conversion + inference.
model
Model specific
python
python script changes
#17141
opened Nov 10, 2025 by
tamarPal
Loading…
llama: introduce support for model-embedded sampling parameters
python
python script changes
#17120
opened Nov 9, 2025 by
taronaeo
Loading…
rpc : fix alloc size logic
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
#17116
opened Nov 9, 2025 by
ggerganov
Loading…
2 tasks
CPU SIMD and pipeline optimizations across vec/mmq/ops/kv-cache/repack
ggml
changes relating to the ggml tensor library for machine learning
#17113
opened Nov 8, 2025 by
NoahOksuz
Loading…
webui : add keyboard shortcut to toggle sidebar
examples
server
#17099
opened Nov 8, 2025 by
danbev
Loading…
Add Metal-4 Tensor API test harness for iOS
examples
#17098
opened Nov 8, 2025 by
ArjunDivecha
Loading…
Previous Next
ProTip!
Add no:assignee to see everything that’s not assigned.