Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
521 Open 6,809 Closed
521 Open 6,809 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

model-conversion : add missing curl script [no ci] examples
#15761 opened Sep 3, 2025 by danbev Loading…
CANN: fix acl_rstd allocation size in ggml_cann_rms_norm Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#15760 opened Sep 3, 2025 by noemotiovon Loading…
1
2
OpenCL: add hs=40 support to FA ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#15758 opened Sep 2, 2025 by rmatif Loading…
feat: add Jinja tester PySide6 simple app python python script changes script Script related
#15756 opened Sep 2, 2025 by pwilkin • Draft
Consolidate multiple tensor copies to reduce API overhead ggml changes relating to the ggml tensor library for machine learning
#15750 opened Sep 2, 2025 by agray3 Loading…
1
1
nix: Added missing packages and options for ROCm build devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
#15747 opened Sep 2, 2025 by SteelPh0enix Loading…
tests : add --list-ops and --show-coverage options testing Everything test related
#15745 opened Sep 2, 2025 by danbev Loading…
ggml-cpu: fixes instability in NNPA Vector Intrinsics documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning
#15739 opened Sep 2, 2025 by taronaeo Loading…
2
1
Add scale_diag_mask_inf_softmax operation for transformer attention ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#15738 opened Sep 2, 2025 by Arya-Hari • Draft
6
CANN: Add RoPE contiguous check for 310I DUO device Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#15735 opened Sep 2, 2025 by hipudding Loading…
1
CANN: Mask unsupported TRANSPOSE_1D operator Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#15733 opened Sep 2, 2025 by hipudding Loading…
1
opencl: initial q8_0 mv support ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#15732 opened Sep 2, 2025 by lhez • Draft
vulkan: Use larger loads in scalar/coopmat1 matmul ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15729 opened Sep 2, 2025 by jeffbolznv Loading…
1
convert : use reflinks for faster conversion demo Demonstrate some concept or idea, not intended to be merged ggml changes relating to the ggml tensor library for machine learning python python script changes
#15727 opened Sep 2, 2025 by compilade • Draft
4 of 13 tasks
vulkan: don't use std::string in load_shaders, to improve compile time ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15724 opened Sep 1, 2025 by jeffbolznv Loading…
2
ggml-cpu : optimize RVV kernels ggml changes relating to the ggml tensor library for machine learning
#15720 opened Sep 1, 2025 by xctan Loading…
1
ggml : block repack support for Q4_K quanti for AArch64 architecture ggml changes relating to the ggml tensor library for machine learning
#15719 opened Sep 1, 2025 by hongyang-7 Loading…
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#15715 opened Sep 1, 2025 by ORippler Loading…
7
vulkan: initialize vulkan-hpp to allow using extension function pointers ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15705 opened Aug 31, 2025 by jeffbolznv Loading…
1
sampling : optimize dist sampler
#15704 opened Aug 31, 2025 by ggerganov Loading…
gguf: gguf_writer refactor ggml changes relating to the ggml tensor library for machine learning
#15691 opened Aug 31, 2025 by Green-Sky Loading…
6
tests: large sizes for get_rows testing Everything test related
#15687 opened Aug 30, 2025 by jeffbolznv • Draft
chat: Fix streaming parser for granite models testing Everything test related
#15682 opened Aug 30, 2025 by shun095 Loading…
1
1
feat: nemotron thinking & toolcalling support testing Everything test related
#15676 opened Aug 29, 2025 by pwilkin Loading…
44
ggml: add ops for WAN video model (cuda && cpu) Apple Metal https://en.wikipedia.org/wiki/Metal_(API) Ascend NPU issues specific to Ascend NPUs 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
#15669 opened Aug 29, 2025 by leejet Loading…
49
ProTip! Adding no:label will show everything without a label.