Skip to content

Tags: djinnome/llama.cpp

Tags

b5173

Toggle b5173's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
mtmd : Support Pixtral 12B (ggml-org#13065)

* add pixtral text model (vision is wip)

* cgraph ok, just missing 2D RoPE

* fix bad rebase

* first working version

* fix problem with img_break token

* support dynamic image size

* update docs

* update test script

b5171

Toggle b5171's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
rpc : add command line option for number of threads for the CPU backe…

…nd (ggml-org#13060)

closes ggml-org#13051

b5170

Toggle b5170's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (ggml-org#13014)

* CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID

* fix logic for RoPE support, CUDA graphs

b5169

Toggle b5169's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
mtmd : support SmolVLM (version 1 and 2) (ggml-org#13050)

* mtmd : support SmolVLM (version 1 and 2)

* correct chat template

* fix n_patches

* scale_factor is an int

* add more models to test

b5166

Toggle b5166's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
llava : update documentations (ggml-org#13055)

* llava : update documentations

* fix typo

b5165

Toggle b5165's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
ggml : add SSE 4.2 and x64 base variant for CPUs without AVX (ggml-or…

…g#12871)

* ggml : add SSE 4.2 variant for CPUs without AVX

* ggml : add x64 base ABI variant

b5164

Toggle b5164's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
SYCL: Add non-contiguous support in ROPE (ggml-org#12993)

ggml-ci

b5163

Toggle b5163's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
mtmd : merge llava, gemma3 and minicpmv CLI into single `llama-mtmd-c…

…li` (ggml-org#13012)

* mtmd : merge `llava-cli` and `gemma3-cli` into single `mtmd-cli`

* support for minicpmv

* remove cpp files of llava and minicpmv

* update hot topics

* mtmd : add not supported msg for qwen2vl

* Update examples/llava/mtmd.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

---------

Co-authored-by: Georgi Gerganov <[email protected]>

b5162

Toggle b5162's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
convert : experimental support for `--mmproj` flag (ggml-org#13023)

* convert : experimental support for `--mmproj` flag

* fix bad ctrl+f replace

* fix style

* split into subclasses TextModel and VisionModel

* rename Mode --> ModelBase

* small fix

* correct CLIP_VISION arch name (because existing GGUF already use it)

* Apply suggestions from code review

Co-authored-by: compilade <[email protected]>

* fix Mistral3Model

* fix typo

Co-authored-by: compilade <[email protected]>

---------

Co-authored-by: compilade <[email protected]>

b5161

Toggle b5161's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
llava: fix errors in clip.h on certain compilers (ggml-org#13030)