Tags: djinnome/llama.cpp
Tags
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
rpc : add command line option for number of threads for the CPU backe… …nd (ggml-org#13060) closes ggml-org#13051
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
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
llava : update documentations (ggml-org#13055) * llava : update documentations * fix typo
SYCL: Add non-contiguous support in ROPE (ggml-org#12993) ggml-ci
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]>
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]>
llava: fix errors in clip.h on certain compilers (ggml-org#13030)
PreviousNext