-
Notifications
You must be signed in to change notification settings - Fork 13.4k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
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…
ggml-cuda: use passed ops instead of hardcoded ops
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#16712
opened Oct 22, 2025 by
am17an
Loading…
mtmd: add mtmd_get_vision_image_size() and mtmd_get_vision_patch_size() functions
examples
#16705
opened Oct 21, 2025 by
deadprogram
Loading…
CUDA: support for weight clamp in top-k norm
documentation
Improvements or additions to documentation
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
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
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…
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…
Vulkan: deduplicate Microsoft Direct3D12 devices
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#16689
opened Oct 20, 2025 by
giladgd
Loading…
Vulkan: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#16686
opened Oct 20, 2025 by
safranowith
Loading…
CUDA: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators
documentation
Improvements or additions to documentation
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
#16683
opened Oct 20, 2025 by
safranowith
•
Draft
RVV1.0 Supported tests for RISC-V
devops
improvements to build systems and github actions
#16682
opened Oct 20, 2025 by
alitariq4589
•
Draft
metal: add ops DIAG_MASK_INF, IM2COL_3D, fix op PAD
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
#16669
opened Oct 19, 2025 by
CLDawes
Loading…
Add Go OCI library integration with go-containerregistry
documentation
Improvements or additions to documentation
#16667
opened Oct 19, 2025 by
ericcurtin
Loading…
sycl: add ROLL operation support
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#16665
opened Oct 19, 2025 by
tamarPal
Loading…
vulkan: Update topk_moe fusion to handle gpt's late softmax
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#16656
opened Oct 18, 2025 by
jeffbolznv
Loading…
graph : add clamping to ffn_moe_weights_sum to avoid div-by-zero
#16655
opened Oct 18, 2025 by
CISC
Loading…
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization
ggml
changes relating to the ggml tensor library for machine learning
#16653
opened Oct 18, 2025 by
JohannesGaessler
Loading…
ggml-cpu: optimise rms_norm op
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
#16650
opened Oct 18, 2025 by
taronaeo
Loading…
vulkan: Optimize SSM_SCAN
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#16645
opened Oct 18, 2025 by
jeffbolznv
Loading…
sycl: use async memory allocation to fix crashes during graph recording
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#16644
opened Oct 17, 2025 by
mmichel11
Loading…
vulkan: Increase BK to 32; use BK/4 for non-CM mul_mm.comp
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#16636
opened Oct 17, 2025 by
SavicStefan
Loading…
metal : initial Metal4 tensor API support
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
#16634
opened Oct 17, 2025 by
ggerganov
Loading…
1 of 2 tasks
ggml: CUMSUM and TRI (CPU, Metal, CUDA)
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
examples
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
testing
Everything test related
#16623
opened Oct 16, 2025 by
gabe-l-hart
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2025-09-22.