Search results

ggml_metal_library_compile_pipeline: failed to compile pipeline: for LFM2-8B-A1B-Q8_0.gguf

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

bugSomething isn't workingSomething isn't working

Status: Open.

Bug

#17603 In ggml-org/llama.cpp;

· leok7v opened on Nov 29, 2025

rpc : fix alloc size logic

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

Status: Open (in progress).

ggml-org/llama.cppnumber 17116

#17116 In ggml-org/llama.cpp;

· ggerganov opened on Nov 9, 2025

[RFC] ggml: new backend for API Remoting

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

buildCompilation issuesCompilation issues

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

Status: Open (in progress).

ggml-org/llama.cppnumber 17072

#17072 In ggml-org/llama.cpp;

· kpouget opened on Nov 7, 2025

sampling : add support for backend sampling

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

buildCompilation issuesCompilation issues

examples

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

Nvidia GPUIssues specific to Nvidia GPUsIssues specific to Nvidia GPUs

server

testingEverything test relatedEverything test related

Status: Open (in progress).

ggml-org/llama.cppnumber 17004

#17004 In ggml-org/llama.cpp;

· danbev opened on Nov 4, 2025

Mamba2 SSD

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

examples

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

modelModel specificModel specific

Nvidia GPUIssues specific to Nvidia GPUsIssues specific to Nvidia GPUs

testingEverything test relatedEverything test related

Status: Draft (not ready).

ggml-org/llama.cppnumber 16982

#16982 In ggml-org/llama.cpp;

· gabe-l-hart opened on Nov 3, 2025

metal: add ops DIAG_MASK_INF, IM2COL_3D, fix op PAD

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

Status: Open (in progress).

ggml-org/llama.cppnumber 16669

#16669 In ggml-org/llama.cpp;

· CLDawes opened on Oct 19, 2025

ggml: CUMSUM and TRI (CPU, Metal, CUDA)

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

examples

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

Nvidia GPUIssues specific to Nvidia GPUsIssues specific to Nvidia GPUs

testingEverything test relatedEverything test related

Status: Open (in progress).

ggml-org/llama.cppnumber 16623

#16623 In ggml-org/llama.cpp;

· gabe-l-hart opened on Oct 16, 2025

metal: add support for LOG op (f32, f16)

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

Status: Open (in progress).

ggml-org/llama.cppnumber 16530

#16530 In ggml-org/llama.cpp;

· RD-zhang1234 opened on Oct 12, 2025

Metal Pool 1D Kernel

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

testingEverything test relatedEverything test related

Status: Open (in progress).

ggml-org/llama.cppnumber 16429

#16429 In ggml-org/llama.cpp;

· ThoreKoritzius opened on Oct 5, 2025

[metal] Add fused RMS_NORM + MUL + SWIGLU for Qwen3Next

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

testingEverything test relatedEverything test related

Status: Open (in progress).

ggml-org/llama.cppnumber 16143

#16143 In ggml-org/llama.cpp;

· MemoryIt opened on Sep 21, 2025

[WIP] Rpc split row

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

examples

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

Status: Open (in progress).

ggml-org/llama.cppnumber 16020

#16020 In ggml-org/llama.cpp;

· LeaveNhA opened on Sep 16, 2025

<code>--numa mirror</code>: mirror model weights to every Numa node in the system

Apple Metalhttps://en.wikipedia.org/wiki/Metal_(API)https://en.wikipedia.org/wiki/Metal_(API)

Ascend NPUissues specific to Ascend NPUsissues specific to Ascend NPUs

devopsimprovements to build systems and github actionsimprovements to build systems and github actions

examples

ggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learning

IBM zDNNissues specific to IBM zDNN Acceleratorissues specific to IBM zDNN Accelerator

Nvidia GPUIssues specific to Nvidia GPUsIssues specific to Nvidia GPUs

OpenCLIssues specific to the OpenCL backendIssues specific to the OpenCL backend

pythonpython script changespython script changes

SYCLhttps://en.wikipedia.org/wiki/SYCL - GPU programming languagehttps://en.wikipedia.org/wiki/SYCL - GPU programming language

testingEverything test relatedEverything test related

VulkanIssues specific to the Vulkan backendIssues specific to the Vulkan backend

Status: Draft (not ready).

ggml-org/llama.cppnumber 16000

#16000 In ggml-org/llama.cpp;

· dbsanfte opened on Sep 15, 2025