head	1.14;
access;
symbols
	pkgsrc-2026Q3:1.13.0.2
	pkgsrc-2026Q3-base:1.13;
locks; strict;
comment	@# @;


1.14
date	2026.09.26.09.45.32;	author wiz;	state Exp;
branches;
next	1.13;
commitid	503fdom2PDeI97XG;

1.13
date	2026.09.12.20.27.32;	author wiz;	state Exp;
branches;
next	1.12;
commitid	ibVyPeNRK3N7anVG;

1.12
date	2026.08.26.10.27.31;	author wiz;	state Exp;
branches;
next	1.11;
commitid	3qeofor0gXtao8TG;

1.11
date	2026.08.23.07.44.35;	author wiz;	state Exp;
branches;
next	1.10;
commitid	mCs7bcys72WeAJSG;

1.10
date	2026.08.19.09.18.48;	author wiz;	state Exp;
branches;
next	1.9;
commitid	ckcSl6Xwwl8xeeSG;

1.9
date	2026.08.19.08.25.29;	author wiz;	state Exp;
branches;
next	1.8;
commitid	x5j8JEyJeltfWdSG;

1.8
date	2026.08.15.08.04.29;	author wiz;	state Exp;
branches;
next	1.7;
commitid	6ob0AIG6GRYUWHRG;

1.7
date	2026.08.08.07.14.51;	author wiz;	state Exp;
branches;
next	1.6;
commitid	2x7bUKr9yCpVTNQG;

1.6
date	2026.08.05.05.35.43;	author wiz;	state Exp;
branches;
next	1.5;
commitid	3zcBYgQTS9IUrpQG;

1.5
date	2026.08.03.17.14.33;	author wiz;	state Exp;
branches;
next	1.4;
commitid	73wrtuiTtQaDndQG;

1.4
date	2026.07.19.07.50.48;	author wiz;	state Exp;
branches;
next	1.3;
commitid	CI59o2EqVtd7KeOG;

1.3
date	2026.07.13.14.35.20;	author wiz;	state Exp;
branches;
next	1.2;
commitid	l67bRCoJluAMavNG;

1.2
date	2026.07.13.10.16.36;	author wiz;	state Exp;
branches;
next	1.1;
commitid	aKYNGOWwcy4BJtNG;

1.1
date	2026.07.02.10.58.21;	author wiz;	state Exp;
branches;
next	;
commitid	cgGQYP2SmaYmk4MG;


desc
@@


1.14
log
@ggml: update to 0.25.3.

0.25.3

A small maintenance release: the core graph size calculation
(ggml_graph_nbytes) no longer triggers a UBSan "non-zero offset to
null pointer" diagnostic, and the CI setup moves CUDA builds to
the hf-jobs runner and adds a new AMD Vulkan build job.

0.25.2

A small point release focused on backend improvements: a new CUDA
convolution kernel with an implicit-GEMM fast path, Vulkan fixes
and tuning (misalignment handling in convolution shaders and
cooperative-matrix support for Adreno GPUs), an optimized DP4A
binary kernel for OpenCL Q6_K GEMM, and a precision guard in the
Hexagon backend.

0.25.1

A hotfix release focused on the CUDA backend: sparse flash attention,
which had been disabled due to a batch-dependent gate, is re-enabled
for long-context prefill (up to ~1.4x prefill speedup at 131k
context), with the supporting sparse mask scan kernel significantly
sped up. Additionally, Metal gains the missing f32 × bf16 matmul
kernels (fixing depthwise convolutions with bf16 weights) and its
flash-attention tuning tables are now keyed by GPU family instead
of individual SKU, while Vulkan adds MMQ/MMV matmul kernels for
the IQ4_XS quantization type.

0.25.0

This release expands hyper-connection, flash-attention, and fused
MoE/SSM support across CPU, GPU, and accelerator backends. It also
improves backend robustness, quantization, data-layout handling,
and RPC/meta buffer management. Numerous correctness fixes and
performance tuning land across all major backends, including new
kernels, fusions, and op coverage.

0.24.0

This release focuses on expanding backend coverage and robustness,
with a new precision-control API, major Vulkan/SYCL/Hexagon/OpenCL
work, and numerous correctness and performance fixes across CPU,
CUDA, Metal, and other backends.
@
text
@$NetBSD: distinfo,v 1.13 2026/09/12 20:27:32 wiz Exp $

BLAKE2s (ggml-0.25.3.tar.gz) = a00d4ec2eb165d2b0077924d8111e5fb5760186ddd42b21976c1c97a1d1b481a
SHA512 (ggml-0.25.3.tar.gz) = 2344cf53dadeb1f1b2fd392aa8ae1850992fa127740a0a78b085be11708fe3c6423bfdd94009d3409c4a99fac7f525d8dfca0ba955526e3ae9b1024a5e73bcbe
Size (ggml-0.25.3.tar.gz) = 4103121 bytes
@


1.13
log
@ggml: update to 0.23.0.

Version 0.23.0 adds new operators and backend scheduling APIs for
sparse attention, asynchronous execution, and allocation-dependency
tracking. It includes broad correctness and performance work across
CPU, GPU, and accelerator backends, plus an expanded RPC stack with
Apple RDMA support.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.12 2026/08/26 10:27:31 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.23.0.tar.gz) = 5d0c4805ea8df62b546455efb40e0bd0175e4f4a80d930512827fd0d75b03b92
SHA512 (ggml-0.23.0.tar.gz) = 5bab13fbe931e4a78759449e91eadad979d1efaf427439c674ebb22639fde32d1468791488b28ae3dda4952dd8c0514b2c4fee9ecc46033f7aff16de442dffc2
Size (ggml-0.23.0.tar.gz) = 3931297 bytes
@


1.12
log
@ggml: update to 0.22.0.

This release adds tensor-split support to the multi-backend (meta)
backend with improved split-state propagation, reworks the Metal
kernels into per-op sources with parallel compilation, and fixes
ggml_clamp to be a proper non-in-place op. It also brings new ops
(POOL_1D, PAD_REFLECT_1D), Q2_K SYCL kernels, MoE bias fusion on
OpenCL, and assorted fixes across the CUDA, Metal, SYCL, Vulkan,
OpenCL and WebGPU backends.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.11 2026/08/23 07:44:35 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.22.0.tar.gz) = c2f40f3079d1d3b54bbdc0fa0bd5f24cf0e3fdb69537f195e6435f5a0604fac3
SHA512 (ggml-0.22.0.tar.gz) = 61ea7d216c949f0e484f2b4edf1a83226e452079ef0663575c1b2585a2960bc1318bdf64da817a89cbe0b3baa4d7cdec81fe33417d55bb4b2e80428486aebd5a
Size (ggml-0.22.0.tar.gz) = 3767077 bytes
@


1.11
log
@ggml: update to 0.21.0.

Changes not found.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.10 2026/08/19 09:18:48 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.21.0.tar.gz) = 9a8caf7042b8d0a75dff333d0e7f9885f6198fdff918dcad6cc81ad185ecc6e1
SHA512 (ggml-0.21.0.tar.gz) = f8a38baa523b3b709541c2e2424d4103977b74821583be2acc3a27fd4806c0eaf2b4209b23759f57a86640da0cc3e35a4b3eeb1af5001b9cd65e1a0a1edf98fc
Size (ggml-0.21.0.tar.gz) = 3744574 bytes
@


1.10
log
@ggml: update to 0.20.2.

Changes not found.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.9 2026/08/19 08:25:29 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.20.2.tar.gz) = d77f0a78db895fe1bdab3ddea5e5799e0c237f69921873579a39dc1b401e2b1a
SHA512 (ggml-0.20.2.tar.gz) = e139a6f3b6d247831a5289b01a10db8ef83d88063e25a3bfe53d992471d4f698a7dabe5df63ec776a9cc95c66a9248c068fbf80b974f0911ccd55692d9ee7930
Size (ggml-0.20.2.tar.gz) = 3718748 bytes
@


1.9
log
@ggml: update to 0.20.1.

No changelog found.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.8 2026/08/15 08:04:29 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.20.1.tar.gz) = ab09c7fc3199032d0b5be6d8a5be1688dd6bd3632cd99ae99a72d4eac6ca99e2
SHA512 (ggml-0.20.1.tar.gz) = b42d28039bfd75c8409f88c1fb762bb21a31a09a47714fae0db9de71b82cffff9c5ed1038a7ff2f6f899d62e781319cdb1f81519eb8768a1a0741ef6b53f1ec1
Size (ggml-0.20.1.tar.gz) = 3718190 bytes
@


1.8
log
@ggml: update to 0.20.0

no summary available
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.7 2026/08/08 07:14:51 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.20.0.tar.gz) = 3b75d4a3a08c5a1c61acab903fff3c61c1a528239c0425e7351e1a459460b3df
SHA512 (ggml-0.20.0.tar.gz) = 547b4338a15d02eab64198065d05225526e69b105300266d82c9649ea801db1d2bf210b4d2d05a142eb1e36d99ee7dbb9c5d1bf43c3d5c213b1b7878c5b6fb82
Size (ggml-0.20.0.tar.gz) = 3716581 bytes
@


1.7
log
@ggml: update to 0.19.0.

No summary found.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.6 2026/08/05 05:35:43 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.19.0.tar.gz) = eca1ff76193bdd112ba6f82262e33fa40840f013e7b542f3d5f7e3d520e95219
SHA512 (ggml-0.19.0.tar.gz) = 6623b64b6703685ec4fd0378daadc6387c5203136406758997a23dff8b315773c1d5ce913121a86d4a51e885045fa1cf5066ea58c5f5cd77c7662a85c1da392d
Size (ggml-0.19.0.tar.gz) = 3657744 bytes
@


1.6
log
@ggml: update to 0.18.1.

Summary not found.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.5 2026/08/03 17:14:33 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.18.1.tar.gz) = 3e0cb3c36647e8534f93ee471639b879aa74157bb68fce6bcf7d79315095c3e6
SHA512 (ggml-0.18.1.tar.gz) = 876e67516d69baf5e2cda08ed95c4369b614286e9d1fd2e9982525581dae73e71d894ae2b0d1e860a0d26a31bbf52dedfe32e98faaea25600bc9e76f7f198b38
Size (ggml-0.18.1.tar.gz) = 3650952 bytes
@


1.5
log
@ggml: update to 0.18.0.

Another two weeks of updates.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.4 2026/07/19 07:50:48 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.18.0.tar.gz) = 929a791d86e38ba4c131777b818dd77f16742b1e6bb47c21eba5fc21ca802d32
SHA512 (ggml-0.18.0.tar.gz) = ba90525a8b46b2f974a89974364d49fc799fb64ef74f6eb3ce9ce39a75c816b64a16b9e6cea917fd5b1fda3d26995f3c7aae9b0afacd8314025e01d55547e1a0
Size (ggml-0.18.0.tar.gz) = 3628930 bytes
@


1.4
log
@ggml: update to 0.17.0.

No changes summary found.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.3 2026/07/13 14:35:20 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.17.0.tar.gz) = 8d4162ff5c8a2886f0083595358c5aaa6a24d9642aea1e06c4cac2b5ce447239
SHA512 (ggml-0.17.0.tar.gz) = 05c264bb2303e5d143aa51b8a33b3e6200d3526efc51ffd57309c3584b6c1286dc8edd97b9eda2949bd59b5a3ea082c2c3ff239efb5bd1ce2dd41d8f58dc0cde
Size (ggml-0.17.0.tar.gz) = 3595353 bytes
@


1.3
log
@ggml: remove patch for stable-diffusion.cpp

stable-diffusion.cpp uses local copy anyway.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.2 2026/07/13 10:16:36 wiz Exp $
d3 3
a5 3
BLAKE2s (ggml-0.16.0.tar.gz) = de9a303430f31b4cd3cf7d6de4c618ed379c50ebc766146f9100bef4794beb91
SHA512 (ggml-0.16.0.tar.gz) = bf573ba140bbbc60d31436c736cf2f7f1bcb49fbd681d512641bce1127004a676a814336f822c2dcce920c5b154f78426a35456826f8bd41fcdcf1f939a73a17
Size (ggml-0.16.0.tar.gz) = 3317288 bytes
@


1.2
log
@ggml: update to 0.16.0.

No summary of changes found.
@
text
@d1 1
a1 1
$NetBSD: distinfo,v 1.1 2026/07/02 10:58:21 wiz Exp $
a5 1
SHA1 (patch-include_ggml.h) = c342dfeafcf9987298b35140e978aeed619f0bfe
@


1.1
log
@math/ggml: import ggml-0.15.3

Tensor library for machine learning

## Features

- Low-level cross-platform implementation
- Integer quantization support
- Broad hardware support
- Automatic differentiation
- ADAM and L-BFGS optimizers
- No third-party dependencies
- Zero memory allocations during runtime
@
text
@d1 1
a1 1
$NetBSD$
d3 3
a5 3
BLAKE2s (ggml-0.15.3.tar.gz) = 7a4eeb168e4d9bf1f6a7aa589b91bc1ca4d9d31096c9143985f0628bb9a56fa0
SHA512 (ggml-0.15.3.tar.gz) = 51dad3310aa28e3daf2689d3617c5f978b50469b4676d101ce7071d0dfbe8b1d04755cc2114cd8ef7ba6dd1466daf6362b0cd42ddf6c9f1a84c3bc43664ec56c
Size (ggml-0.15.3.tar.gz) = 3227851 bytes
@