3 people 62df1815bc cuda, hip: GDN chunked kernel (#29353) ...

* cuda, hip: GDN chunked kernel

Ported-from: https://github.com/tetherto/qvac-fabric-llm.cpp/pull/257
Source-commit: 53f0027d8070715fe9ad2131f3201bb0001d4eed
Co-authored-by: Aman Gupta <aman.gupta@tether.io>

* fix older builds

* review fixes

* cuda: enable GDN MMA on tested Ampere and Ada GPUs

Enable SM86 and SM89 after RTX 3090 and RTX 4090 correctness and prefill benchmarks. Keep other untested architectures on the existing fallback.

Assisted-by: Codex

* cuda : use refactored swizzle API in GDN MMA

* ggml : GDN only guarantees the final state when n_tokens > K

* cuda : add short GDN MMA phase comments

---------

Co-authored-by: gianni-cor <gianfranco.cordella@tether.io>
Co-authored-by: Aman Gupta <aman.gupta@tether.io>

2026-10-14 22:00:58 +08:00

..

ggml-alloc.h

ggml : add alloc_buffer_n to buffer type interface (#23671)

2026-10-02 11:08:08 +03:00

ggml-backend.h

llama : report compute graph reallocations during inference (#30329)

2026-10-12 11:53:58 +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.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

RPC: add -sm tensor (#26610)

2026-10-06 20:55:39 +05:30

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

cuda, hip: GDN chunked kernel (#29353)

2026-10-14 22:00:58 +08:00

gguf.h

gguf : add tensor shape accessor (#24405)

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