xrip 60c62ce9f2 Merge upstream master; take upstream DFlash2, MMQ fusion, and top-k ...

Assisted-by: GLM-5.3-Flash

2026-11-01 22:29:01 +03:00

..

ggml-alloc.h

Merge upstream master

2026-10-06 12:03:55 +03:00

ggml-backend.h

Merge upstream master; take upstream DFlash2, MMQ fusion, and top-k

2026-11-01 22:29:01 +03:00

ggml-blas.h

ggml : build backends as libraries (#10256)

2024-11-14 18:04:35 +01:00

ggml-cann.h

docs : Minor cleanups (#19252)

2026-02-02 08:38:55 +02:00

ggml-cpp.h

ggml : fix ggml_gallocr_ptr type (ggml/1205)

2025-05-01 09:58:44 +03:00

ggml-cpu.h

kleidiai: Add SME vs SME2 distinction in kernel dispatch (#25478)

2026-07-16 08:57:04 -07:00

ggml-cuda-gdn-transaction.h

llama: add opt-in SM75 recurrent state replay

2026-09-21 20:56:53 +03:00

ggml-cuda.h

CUDA: remove -sm row, refactor cuBLAS (#24216)

2026-07-06 20:04:53 +02:00

ggml-et.h

ggml-et: Initial ET backend (#24179)

2026-07-10 12:38:34 +08:00

ggml-hexagon.h

Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)

2025-10-22 13:47:09 -07:00

ggml-metal.h

metal : refactor + optimize v2 (#15995)

2025-09-17 20:38:12 +03:00

ggml-opencl.h

Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)

2024-12-13 12:23:52 -08:00

ggml-openvino.h

ggml : add OpenVINO backend (#15307)

2026-03-14 07:56:55 +02:00

ggml-opt.h

chore : correct typos [no ci] (#20041)

2026-03-05 08:50:21 +01:00

ggml-rpc.h

llama: create new fused op for QSA mask (#30640)

2026-10-22 01:02:22 +08:00

ggml-sycl.h

sycl : fix compile warnings

2026-09-23 11:47:24 +03:00

ggml-virtgpu.h

ggml-virtgpu: make the code thread safe (#19204)

2026-02-04 10:46:18 +08:00

ggml-vulkan.h

vulkan: Make Vulkan optional at runtime (#11493). (#11494)

2025-02-10 07:17:21 +01:00

ggml-webgpu.h

ggml: Add initial WebGPU backend (#14521)

2025-07-16 18:18:51 +03:00

ggml-zdnn.h

ci: add zdnn backend build but not test (#29541)

2026-09-29 20:45:14 +03:00

ggml-zendnn.h

ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690)

2025-12-07 00:13:33 +08:00

ggml.h

Quant: OCP FP8 E4M3 support (#27512)

2026-10-29 18:14:37 +01:00

gguf.h

gguf : add tensor shape accessor (#24405)

2026-07-13 13:55:15 +03:00