-
Notifications
You must be signed in to change notification settings - Fork 13.1k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
ci : disable AMD workflows + update NVIDIA workflows
devops
improvements to build systems and github actions
#16200
opened Sep 23, 2025 by
ggerganov
Loading…
Enhance text file detection logic for file attachments
examples
server/webui
server
#16199
opened Sep 23, 2025 by
allozaur
Loading…
Implement progress bar and multi-connection downloads
#16196
opened Sep 23, 2025 by
ericcurtin
Loading…
ggml-cpu: implement MXFP4 SIMD for s390x
ggml
changes relating to the ggml tensor library for machine learning
#16193
opened Sep 23, 2025 by
taronaeo
Loading…
ggml webgpu: support for rope,div,sub,glu,scale,cont operators
ggml
changes relating to the ggml tensor library for machine learning
python
python script changes
testing
Everything test related
#16187
opened Sep 23, 2025 by
reeselevine
Loading…
common : use cpp-httplib as a cURL alternative for downloads
#16185
opened Sep 22, 2025 by
angt
Loading…
ci: run the x64 and arm ci on the github machines instead
devops
improvements to build systems and github actions
testing
Everything test related
#16183
opened Sep 22, 2025 by
netrunnereve
•
Draft
vulkan: handle mat_mul with A matrix > 4GB
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#16176
opened Sep 22, 2025 by
jeffbolznv
Loading…
minor: root cause in error message if loading backend library fails
ggml
changes relating to the ggml tensor library for machine learning
#16172
opened Sep 22, 2025 by
rlewczuk
Loading…
CANN: improve ACL graph matching
Ascend NPU
issues specific to Ascend NPUs
ggml
changes relating to the ggml tensor library for machine learning
#16166
opened Sep 22, 2025 by
noemotiovon
Loading…
vulkan: support arbitrary KV dimension in flash attention
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#16160
opened Sep 21, 2025 by
jeffbolznv
Loading…
webui: switch to hash-based routing (alternative of #16079)
bugfix
fixes an issue or bug
examples
server/webui
server
#16157
opened Sep 21, 2025 by
isaac-mcfadyen
Loading…
vulkan: throw system error instead of SIGABRT during init on older devices
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#16156
opened Sep 21, 2025 by
DmyMi
Loading…
sycl: add PAD_REFLECT_D1 operator support
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#16145
opened Sep 21, 2025 by
ye-NX
Loading…
README.md : Added link to llama-cpp-jna Java binding
#16144
opened Sep 21, 2025 by
romantal
Loading…
[metal] Add fused RMS_NORM + MUL + SWIGLU for Qwen3Next
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
#16143
opened Sep 21, 2025 by
MemoryIt
Loading…
vulkan: 64-bit im2col
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#16135
opened Sep 20, 2025 by
jeffbolznv
Loading…
CUDA: add a fused top-K MoE kernel
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
testing
Everything test related
#16130
opened Sep 20, 2025 by
am17an
Loading…
rpc : use GGML_LOG_* for logging
examples
ggml
changes relating to the ggml tensor library for machine learning
#16129
opened Sep 20, 2025 by
rgerganov
Loading…
mtmd: more optimized build_rope_2d
examples
testing
Everything test related
#16126
opened Sep 20, 2025 by
ngxson
Loading…
Previous Next
ProTip!
Adding no:label will show everything without a label.