Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
562 Open 7,453 Closed
562 Open 7,453 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

CUDA: Remove unneded bias/gate dims in fused mmvq ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16858 opened Oct 30, 2025 by ORippler Loading…
3
CUDA: add expert reduce kernel ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#16857 opened Oct 30, 2025 by am17an Loading…
6
cann: update L2_NORM op support Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#16856 opened Oct 30, 2025 by TecJesh Loading…
3
server/public_simplechat - basic builtin data store related tool calls added - use builtin browser/client side tool calling with minimal setup examples python python script changes server
#16852 opened Oct 29, 2025 by hanishkvc Loading…
2
webui: recognize AsciiDoc files as valid text files examples server
#16850 opened Oct 29, 2025 by jhradilek Loading…
2
vendor : update cpp-httplib to 0.27.0
#16846 opened Oct 29, 2025 by angt Loading…
Enable CUDA graphs for embed gemma 300m ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16844 opened Oct 29, 2025 by ArshM17-NV Loading…
CUDA: Volta tensor core support for MMF ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16843 opened Oct 29, 2025 by JohannesGaessler Loading…
9
improve CUDA cpy memory bandwidth when copying transposed tensor ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#16841 opened Oct 29, 2025 by bssrdf Loading…
6
vulkan : refactor buffer handling in vk_op_f32 ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16840 opened Oct 29, 2025 by Acly • Draft
3
clip : use FA Apple Metal https://en.wikipedia.org/wiki/Metal_(API) examples ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#16837 opened Oct 29, 2025 by ggerganov • Draft
1 task
6
ggml-hexagon: respect input size when getting/setting tensor data ggml changes relating to the ggml tensor library for machine learning
#16836 opened Oct 29, 2025 by l3utterfly Loading…
3
hip: add RDNA4 support for mmf and mma ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16835 opened Oct 29, 2025 by zhang-hui-yulo Loading…
12
cpu: introduce chunking for repack matmuls and enable matmul-id chunking ggml changes relating to the ggml tensor library for machine learning
#16833 opened Oct 29, 2025 by max-krasnyansky Loading…
1
Model: Minimax M2 python python script changes testing Everything test related
#16831 opened Oct 28, 2025 by pwilkin Loading…
2
CUDA: Conv2d tensor core ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16828 opened Oct 28, 2025 by mnehete32 • Draft
1
vulkan: remove the need for the dryrun ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16826 opened Oct 28, 2025 by jeffbolznv Loading…
1
docs: explain CUDA 11 compilation [no ci] documentation Improvements or additions to documentation
#16824 opened Oct 28, 2025 by JohannesGaessler Loading…
3
server/public_simplechat client ui show reasoning support added, toolcalling with direct builtin tools and beyond also in PR chain examples python python script changes server
#16819 opened Oct 28, 2025 by hanishkvc Loading…
2
server : remove n_past examples server
#16818 opened Oct 28, 2025 by ggerganov Loading…
18
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#16817 opened Oct 28, 2025 by yael-works Loading…
4
llama: Fused QKV multiplication
#16813 opened Oct 28, 2025 by am17an • Draft
6
ggml webgpu: minor set rows optimization ggml changes relating to the ggml tensor library for machine learning
#16810 opened Oct 27, 2025 by reeselevine Loading…
ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#16805 opened Oct 27, 2025 by duduta Loading…
6
vulkan: Fix crash when FP16 mul_mat accumulation is not supported ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16796 opened Oct 27, 2025 by rillomas Loading…
9
ProTip! Follow long discussions with comments:>50.