Skip to content

Releases: ggml-org/llama.cpp

b10502

Choose a tag to compare

@github-actions github-actions released this 19 Aug 13:26
0adcc3b

v0.1.2

v0.1.2 Pre-release
Pre-release

Choose a tag to compare

@github-actions github-actions released this 18 Aug 10:23

Note

Semantic versioning is still work in progress.
More info can be found in https://github.com/ggml-org/ggml/discussions/1579

Nightly build: b10485

Change log since v0.1.1

1511ce3 sync : ggml
da786dc ggml : bump version to 0.20.2 (ggml/1589)
27e345b build : fix xcframework + cmake clean-up (#27304)
8b86400 ci : create pre-release with change log and nightly link in make-release (#27302)
25ae3a9 CUDA: MMVQ nwarps=8 for bs=1 for dense models on DGX Spark (#26843)
01818e4 ui: enforce alphabetical enum member ordering (#27272)
0021a77 ui: Refactor Built-In Tools naming (Server/Browser) (#27271)
058df67 ci: more optimizations (#26983)
087f94d doc: document MCP stdio servers and CORS defaults in the server README [no release] [no ci] (#26847)
533b182 server: save processed mtmd chunks as placeholder (#27278)
ed1c3a2 mtmd: use sha256 for input hashing (#27274)
d8df12e vocab : support integer tokenizer scores (#27260)
b75ecd1 mtmd : skip thumbnail for non-tiled LFM2 images (#27246)
60eeeb6 cuda : skip UMA override for HIP builds (#27083)
39be55c vendor: move hash to vendor (#27262)

b10488

Choose a tag to compare

@github-actions github-actions released this 18 Aug 11:05
9d77fa1

ci : Update OpenVINO to 2026.3, skip nemotron-h rollback test (#27292)

  • update to ov-2026.3, update device drivers

  • ci: skip nemotron-h rollback test on OpenVINO

The OpenVINO backend does not support SSM_SCAN, so the Nemotron-H recurrent state rollback graph is split and cannot preserve the recurrent cache output shape. Keep the test enabled for other backends and retain the qwen35 OpenVINO rollback coverage.


Co-authored-by: ravi9 ravi.panchumarthy@intel.com

Website:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b10486

Choose a tag to compare

@github-actions github-actions released this 18 Aug 10:43
7acdbb1

mtmd: fix LFM2 image tiling threshold (#27057)

  • mtmd: fix LFM2 image tiling threshold

  • refactor testing

  • fix

  • fix on windows


Co-authored-by: Xuan Son Nguyen son@huggingface.co

Website:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b10485

Choose a tag to compare

@github-actions github-actions released this 18 Aug 10:08

b10483

Choose a tag to compare

@github-actions github-actions released this 18 Aug 09:24
27e345b

build : fix xcframework + cmake clean-up (#27304)

  • xcframework : fix build

  • mtmd : remove unused include path

  • vendor : use vendor::hash alias target in cmake

CMake reserves "::" in target names for imported/alias targets, so the real
target keeps the name vendor-hash and a vendor::hash ALIAS target is added.
Consumers (mtmd, llama-gguf-hash) now link against the namespaced alias.

Assisted-by: pi:llama.cpp/Qwen3.8-27B

  • vendor : add cmake targets for all vendored libs with vendor:: aliases

Add INTERFACE targets for the header-only vendor libs (miniaudio, nlohmann,
sheredom, stb) and ALIAS targets named vendor:: for all of them,
including cpp-httplib and hash. Each exposes the vendor/ root so includes
are namespaced, e.g. <nlohmann/json.hpp>.

Consolidate the per-lib add_subdirectory calls into a single
add_subdirectory(vendor), keeping the cpp-httplib gate on LLAMA_BUILD_COMMON.
Consumers (llama-common, mtmd) now link the aliases instead of relying on
raw vendor/ include paths.

hash: consumers now include via "hash/hash.h"; the vendor/hash dir is kept
as a PRIVATE include so the synced upstream sources compile unmodified.

Assisted-by: pi:llama.cpp/Qwen3.8-27B

  • readme : use foo/bar names in acknowledgements

Assisted-by: pi:llama.cpp/Qwen3.8-27B

  • ocd : fix valign

Website:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b10472

Choose a tag to compare

@github-actions github-actions released this 17 Aug 17:16
60eeeb6

cuda : skip UMA override for HIP builds (#27083)

AMD APUs report accurate memory via hipMemGetInfo. Using
MemAvailable over-promises on small-carveout systems.

fixes #18159

Website:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b10470

Choose a tag to compare

@github-actions github-actions released this 17 Aug 13:59
34af94c

ci : push release tag explicitly in release.yml (#27261)

Add a "Create and push git tag" step to the release job, right before
the "Create release" step. The tag is created with git tag and pushed
with the deploy key already configured by the Clone step, instead of
relying on the Releases API (action-create-release) to create it as a
side effect.

The tag is lightweight, matching all existing b release tags.
The step is idempotent: if the tag already exists (e.g. on a re-run),
creation and push are skipped.

Assisted-by: pi:llama.cpp/Qwen3.8-27B

Website:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b10456

Choose a tag to compare

@github-actions github-actions released this 17 Aug 06:29
f275595

sycl: fix thread/block count in quantized cpy kernel launches (#27160)

Adjusts the thread/block count to be proportional to the size
of the quant, reducing under/over subscription.

Largest perf improvement is the q4_0 -> f32 path, with, on
a Arc 70, throughput goes from 20.21 GB/s to 158.19 GB/s

The rest of the quants are flat in performance uplift.

Website:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b10455

Choose a tag to compare

@github-actions github-actions released this 17 Aug 05:47
37a215c

[SYCL] support OP OPT_STEP_ADAMW, OPT_STEP_SGD (#25268)

  • fix conflict

  • fix conflict of ops.md

  • fix conflict of ops.md

  • update the ops.md


Co-authored-by: Neo Zhang Jianyu jianyu.zhang@intel.com

Website:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI: