2 Commits

Author	SHA1	Message	Date
Lingfeng Ren	35845dd975	server : support MTP with multimodal prompts (#1758) ... Synchronize MTP state after mtmd decode batches so multimodal prompt chunks do not desync the draft context.	2026-05-11 09:51:07 +03:00
Kawrakow	c1a0e15377	Port mdmd from mainline + Qwen2/2.5-VL support (#798) ... * Add mtmd: the beginning * Add mtmd: mtmd.cpp compiles * Add mtmd: clip initialization compiles * Add mtmd: clip.cpp compiles * Add mtmd: builds successfully * Add CPU implementation for GGML_OP_GLU * Add CUDA implementation for GGML_OP_GLU * Add CPU implementation for GGML_OP_CONV_2D and GGML_OP_CONV_2D_DW * Add CUDA implementation for GGML_OP_CONV_2D and GGML_OP_CONV_2D_DW * Add mtmd: refresh CPU rope * Add mtmd: refresh CUDA rope * Add mtmd: add Qwen2-VL * Add mtmd: Qwen2.5-VL text seems to work with this change * Add mtmd: fix swiglu * Add mtmd: use LOG_TEE so generated tokens show up in terminal * Add mtmd: do not attempt to load a GPU backend if none are available * GLU, not GPU * Fix typo * Fix new/free mismatch * LOG stuff * Add mtmd: this fixes gibberish on second image --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>	2025-09-27 08:45:29 +02:00