- Notifications
You must be signed in to change notification settings - Fork14.2k
Pull requests: ggml-org/llama.cpp
Author
Uh oh!
There was an error while loading.Please reload this page.
Label
Uh oh!
There was an error while loading.Please reload this page.
Projects
Uh oh!
There was an error while loading.Please reload this page.
Milestones
Uh oh!
There was an error while loading.Please reload this page.
Reviews
Assignee
Assigned to nobodyLoading
Uh oh!
There was an error while loading.Please reload this page.
Sort
Pull requests list
ci : only save ccache on master devopsimprovements to build systems and github actions
#18207 openedDec 19, 2025 byCISCLoading…
Fix BLAS Compile Definitions ggmlchanges relating to the ggml tensor library for machine learning
#18205 openedDec 19, 2025 byDaAwesomePLoading…
HIP: Use mmq on MFMA devices for MUL_MAT_ID in cases where a lot of splits would be generated ggmlchanges relating to the ggml tensor library for machine learning Nvidia GPUIssues specific to Nvidia GPUs
#18202 openedDec 19, 2025 byIMbackKLoading…
ci : remove non-windows zip artifacts devopsimprovements to build systems and github actions
#18201 openedDec 19, 2025 byCISCLoading…
llamafile: add rvv support for sgemm kernels ggmlchanges relating to the ggml tensor library for machine learning
#18199 openedDec 19, 2025 bytaimur-10xLoading…
cmake: Added more x86_64 CPU backends when building withchanges relating to the ggml tensor library for machine learning
GGML_CPU_ALL_VARIANTS=On ggmlvulkan: fix im2col overflowing maxworkgroupcount ggmlchanges relating to the ggml tensor library for machine learning testingEverything test related VulkanIssues specific to the Vulkan backend
#18180 openedDec 18, 2025 byjeffbolznvLoading…
vulkan: Warptile tuning for Intel Xe2/Xe3 ggmlchanges relating to the ggml tensor library for machine learning VulkanIssues specific to the Vulkan backend
#18178 openedDec 18, 2025 byvirajwadLoading…
tool/ex/tests: consistently free ctx, then model examples testingEverything test related
#18168 openedDec 18, 2025 byJohannesGaesslerLoading…
spm: make llama a dynamic library; leave placeholder for ggml/gguf na…
#18165 openedDec 18, 2025 bysteven-moonLoading…
ggml-hexagon: gelu optimization ggmlchanges relating to the ggml tensor library for machine learning
#18151 openedDec 17, 2025 byjoeldushouyu • Draft
ggml-cpu: fix todo comment #15953 and SIMD-like calculate 4 elems ggmlchanges relating to the ggml tensor library for machine learning
#18150 openedDec 17, 2025 byGermanAizekLoading…
[WIP] Enable cooperative matrix support for Intel Arrow Lake H GPUs ggmlchanges relating to the ggml tensor library for machine learning VulkanIssues specific to the Vulkan backend
server: validate n_batch == n_ubatch for embeddings (#6263) examples server
#18123 openedDec 17, 2025 byyifant-code • Draft
[WIP] Cross Entropy Loss on Metal Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API) ggmlchanges relating to the ggml tensor library for machine learning
ggml-hexagon: Add lightweight atomic synchronization support to htp_ops_context for inter-task coordination ggmlchanges relating to the ggml tensor library for machine learning
#18113 openedDec 16, 2025 byngdxzyLoading…
ggml-cuda: Delta-Net linear attention for Qwen3-Next ggmlchanges relating to the ggml tensor library for machine learning modelModel specific Nvidia GPUIssues specific to Nvidia GPUs testingEverything test related
#18102 openedDec 16, 2025 byhauhautLoading…
vulkan/cuda: fix topk_moe with exp_probs_b ggmlchanges relating to the ggml tensor library for machine learning Nvidia GPUIssues specific to Nvidia GPUs testingEverything test related VulkanIssues specific to the Vulkan backend
#18071 openedDec 15, 2025 byjeffbolznvLoading…
webui: add responsive chat width option to webui (#18067) examples server
#18068 openedDec 15, 2025 byImadSaddikLoading…
vulkan: support GGML_UNARY_OP_XIELU ggmlchanges relating to the ggml tensor library for machine learning VulkanIssues specific to the Vulkan backend
#18062 openedDec 15, 2025 byjeffbolznvLoading…
vulkan: in graph_optimize, try to group ADD operations ggmlchanges relating to the ggml tensor library for machine learning VulkanIssues specific to the Vulkan backend
#18060 openedDec 15, 2025 byjeffbolznvLoading…
ProTip! Exclude everything labeled
bug with-label:bug.