Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
641 Open 8,574 Closed
641 Open 8,574 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

Metal : Supplement floor operator
#18878 opened Jan 16, 2026 by Old-cpu Loading…
Try fixing non-ASCII parameters in llama-cli on Windows examples
#18872 opened Jan 16, 2026 by forshtat • Draft
opencl: add optimized q8_0 mm kernel for adreno ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#18871 opened Jan 15, 2026 by shaofeiqi • Draft
1
feat: Add file descriptor based model loading for Android SAF support ggml changes relating to the ggml tensor library for machine learning
#18870 opened Jan 15, 2026 by Siddhesh2377 Loading…
3
convert_hf_to_gguf.py: refactor modify_tensors to call super python python script changes
#18866 opened Jan 15, 2026 by am17an Loading…
13
sampling : update outdated comment about has_sampled [no ci]
#18863 opened Jan 15, 2026 by danbev Loading…
sampling : add support for saving/loading backend sampling state testing Everything test related
#18862 opened Jan 15, 2026 by danbev • Draft
1
wasm, tests: fix ctests with emscripten build Compilation issues ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#18861 opened Jan 15, 2026 by aviallon • Draft
2
ggml-cpu: aarm64: q5_K repack gemm and gemv (and generic) implementations (i8mm) ggml changes relating to the ggml tensor library for machine learning
#18860 opened Jan 15, 2026 by Alcpz Loading…
4
ggml-cpu: add RVV vec dot kernels for quantization types ggml changes relating to the ggml tensor library for machine learning
#18859 opened Jan 15, 2026 by rehan-10xengineer Loading…
ggml-cpu: add q4_0 repack support for wasm ggml changes relating to the ggml tensor library for machine learning
#18858 opened Jan 15, 2026 by aviallon • Draft
4
enforce response_format and json_schema for Kimi K2 testing Everything test related
#18851 opened Jan 15, 2026 by akoumjian Loading…
1
Deepseek v3.2 dense attention support from @fairydreaming python python script changes
#18849 opened Jan 14, 2026 by createthis Loading…
3
kv-cache : optimize KQ mask construction
#18842 opened Jan 14, 2026 by ggerganov Loading…
1
# [RFC] Integrate sparse-ternary-fma for TQ2_0 quantization ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#18836 opened Jan 14, 2026 by HyperFoldUK Loading…
1
vulkan: Revert forced full subgroup for FlashAttention ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18831 opened Jan 14, 2026 by rillomas Loading…
2
model: Add PaddleOCR-VL model support examples model Model specific python python script changes
#18825 opened Jan 14, 2026 by megemini Loading…
@ngxson
7
ggml-backend: Separate dynamic lib install and search paths, add relative search ggml changes relating to the ggml tensor library for machine learning
#18817 opened Jan 13, 2026 by DaAwesomeP Loading…
10
HIP: tune mmq/rocblas switching for RDNA4 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18816 opened Jan 13, 2026 by jiachengjason Loading…
3
sampling : remove sampling branching in output_reserve
#18811 opened Jan 13, 2026 by danbev Loading…
llama: fix integer type consistency in split helpers
#18798 opened Jan 13, 2026 by MaheshJakkala Loading…
5
Unified delta net handling for Qwen3Next and Kimi Linear models model Model specific
#18792 opened Jan 12, 2026 by pwilkin Loading…
16
server: fix memory reservations in populate_token_probs examples server
#18787 opened Jan 12, 2026 by l-austenfeld Loading…
ggml-cpu: add RVV vec dot kernels for quantization types ggml changes relating to the ggml tensor library for machine learning
#18784 opened Jan 12, 2026 by taimur-10x • Draft
webui : send both backend_sampling == false/true examples server
#18781 opened Jan 12, 2026 by ggerganov Loading…
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.