Skip to content

Pull requests: ggml-org/llama.cpp

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

metal: SSM kernel improvements
#17876 opened Dec 8, 2025 by gabe-l-hart Loading…
CUDA: fix FP16 overflow in tile FA kernel
#17875 opened Dec 8, 2025 by JohannesGaessler Loading…
Vulkan: Improve mul_mat_vec_iq1_s speed
#17874 opened Dec 8, 2025 by lovedheart Loading…
Add DIAG for CUDA ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17873 opened Dec 8, 2025 by pwilkin Loading…
vulkan: Allow non-pow2 n_experts in topk_moe ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#17872 opened Dec 8, 2025 by jeffbolznv Loading…
ggml : allow fill node alloc inplace ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17870 opened Dec 8, 2025 by CISC Loading…
fix: Provide macos-specific backtrace printing to avoid terminal death bugfix fixes an issue or bug ggml changes relating to the ggml tensor library for machine learning macos Issues specific to macOS
#17869 opened Dec 8, 2025 by gabe-l-hart Loading…
metal: use shared buffers on eGPU Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#17866 opened Dec 8, 2025 by jdemeule Loading…
Add support for R-4B multimodal model examples python python script changes
#17840 opened Dec 7, 2025 by infil00p Draft
[SYCL] fix softmax for iGPU ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#17838 opened Dec 7, 2025 by NeoZhangJianyu Loading…
debug:Adding CPU-side visual trace for hexagon ggml changes relating to the ggml tensor library for machine learning script Script related
#17837 opened Dec 7, 2025 by Ethan-a2 Loading…
[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4, swiglu_oai 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
#17826 opened Dec 6, 2025 by NeoZhangJianyu Loading…
cann : fix ops broken by circular padding guard Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#17825 opened Dec 6, 2025 by CISC Loading…
cli: new CLI experience devops improvements to build systems and github actions examples script Script related server testing Everything test related
#17824 opened Dec 6, 2025 by ngxson Draft
6 tasks done
llama : add token matching support to llama-grammar testing Everything test related
#17816 opened Dec 6, 2025 by aldehir Loading…
3 tasks done
CANN: support gated linear attn Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#17814 opened Dec 6, 2025 by YushengZhao Loading…
vulkan: faster q6_k matmul ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#17813 opened Dec 6, 2025 by netrunnereve Loading…
model: support Rnj-1 model Model specific python python script changes
#17811 opened Dec 6, 2025 by philip-essential Loading…
ProTip! Adding no:label will show everything without a label.