Skip to content

Releases: ggml-org/llama.cpp

b11020

b11020 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 11:07
7f6f0c2

b11019

b11019 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 10:35
81aeaeb

gguf : align the data section relative to the GGUF start, not the file (#28993)

  • gguf : align the data section relative to the GGUF start, not the file

gguf_init_from_file_ptr reads a GGUF from the current file position, but padded
the data section from file offset 0, so a GGUF embedded at an offset that is not
a multiple of the alignment loaded without error and returned wrong tensor data.

Also adds llama_adapter_lora_init_from_file_ptr, and disables mmap with a warning
when an embedded data section is not aligned, instead of asserting in ggml.

Assisted-by: Claude Opus 5

  • llama : load lora from path through the FILE* variant

The test now checks that mmap is disabled only for an unaligned offset.

Assisted-by: Claude Fable 5.1

  • Update ggml/src/gguf.cpp

Co-authored-by: Johannes Gäßler johannesg@5d6.de

  • Update include/llama.h

Co-authored-by: Johannes Gäßler johannesg@5d6.de

  • llama : error on unaligned mmap of an embedded GGUF, drop test-load-file-ptr

Co-authored-by: Johannes Gäßler johannesg@5d6.de

Website:

Attestations:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

  • DISABLED
  • openEuler x86 (310p)
  • openEuler x86 (910b, ACL Graph)
  • openEuler aarch64 (310p)
  • openEuler aarch64 (910b, ACL Graph)

UI:

b11018

b11018 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 09:58
c9a5eee

b11017

b11017 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 09:27
7490357

b11016

b11016 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 08:58
817e5f8

b11015

b11015 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 08:29
c57da6f

b11013

b11013 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 07:50
05f2dcf

vulkan: fix buffer_reference alignment in im2col shaders (#28996)

Both im2col.comp and im2col_3d.comp declare D_ptr without an explicit
buffer_reference_align, so glslang emits writes through it as Aligned
16. The shaders advance the pointer by D_SIZE, a per-variant define
set to 4 for float and 2 for float16_t, so most write addresses are
not 16-byte aligned. This triggers
VUID-RuntimeSpirv-PhysicalStorageBuffer64-06315 under GPU-AV.

Declaring buffer_reference_align = D_SIZE matches the alignment to the
actual write stride and takes validation hits from 20 to 0 for both
IM2COL and IM2COL_3D.

Fixes #28960

Website:

Attestations:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

  • DISABLED
  • openEuler x86 (310p)
  • openEuler x86 (910b, ACL Graph)
  • openEuler aarch64 (310p)
  • openEuler aarch64 (910b, ACL Graph)

UI:

b11012

b11012 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 06:27
35822af

b11011

b11011 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 02:48
aa39d7a

b11010

b11010 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 17 Sep 00:01
4bc272f