-
Notifications
You must be signed in to change notification settings - Fork 12.8k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
llama: use FA + max. GPU layers by default
python
python script changes
script
Script related
#15434
opened Aug 19, 2025 by
JohannesGaessler
Loading…
CUDA: replace GGML_CUDA_F16 with CUDA arch checks
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#15433
opened Aug 19, 2025 by
JohannesGaessler
Loading…
vulkan: shorten pipeline name strings
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#15431
opened Aug 19, 2025 by
jeffbolznv
Loading…
vulkan: optimize mul_mat_id loading row ids into shared memory
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#15427
opened Aug 19, 2025 by
jeffbolznv
Loading…
Make Mistral community chat templates optional
python
python script changes
#15420
opened Aug 19, 2025 by
juliendenize
Loading…
[CANN] Optimize RMS_NORM using cache
Ascend NPU
issues specific to Ascend NPUs
ggml
changes relating to the ggml tensor library for machine learning
#15419
opened Aug 19, 2025 by
noemotiovon
Loading…
support interns1-mini
python
python script changes
#15412
opened Aug 19, 2025 by
RunningLeon
Loading…
vulkan: Reuse conversion results in prealloc_y
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#15410
opened Aug 18, 2025 by
jeffbolznv
Loading…
Thinking model disabled agent prefill
examples
server
#15404
opened Aug 18, 2025 by
gabe-l-hart
Loading…
vulkan : support ggml_mean
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#15393
opened Aug 18, 2025 by
Acly
Loading…
vulkan : support conv_2d_dw with f16 weights
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#15392
opened Aug 18, 2025 by
Acly
Loading…
Add Trigger at PR creation
devops
improvements to build systems and github actions
#15386
opened Aug 18, 2025 by
alitariq4589
Loading…
fix: Add conditional compilation for OpenCL 2.0 compatibility
ggml
changes relating to the ggml tensor library for machine learning
OpenCL
Issues specific to the OpenCL backend
#15383
opened Aug 18, 2025 by
baonudesifeizhai
Loading…
vulkan: optimize mxfp4
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#15363
opened Aug 16, 2025 by
lovedheart
Loading…
Add option to disable MMA support on Turing
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#15360
opened Aug 16, 2025 by
pt13762104
Loading…
sched : copy only the used experts when offloading prompt processing
ggml
changes relating to the ggml tensor library for machine learning
#15346
opened Aug 15, 2025 by
slaren
Loading…
CANN: fix ggml_cann_rms_norm
Ascend NPU
issues specific to Ascend NPUs
ggml
changes relating to the ggml tensor library for machine learning
#15331
opened Aug 14, 2025 by
yuchuan-cao
Loading…
aLoRA Support
examples
python
python script changes
server
#15327
opened Aug 14, 2025 by
gabe-l-hart
Loading…
1 task done
OpenCL: add fused group_norm/norm, mul, add
ggml
changes relating to the ggml tensor library for machine learning
OpenCL
Issues specific to the OpenCL backend
testing
Everything test related
#15314
opened Aug 14, 2025 by
rmatif
Loading…
Add OpenVINO backend
devops
improvements to build systems and github actions
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
64 bit CUDA copy routines via GGML_CUDA_ALLOW_LARGE_TENSORS
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#15298
opened Aug 13, 2025 by
createthis
Loading…
ggml: riscv: add riscv spacemit backend
build
Compilation issues
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
#15288
opened Aug 13, 2025 by
alex-spacemit
Loading…
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.