koboldcpp/tools
Saba Fallah da3f990a47
mtmd: Add DeepSeekOCR 2 Support (#20975)
* mtmd: DeepSeek-OCR 2 support, with multi-tile dynamic resolution

* introduced clip_image_f32::add_viewsep

* address PR review

- drop redundant ggml_cpy ops in both deepseekocr versions build
- drop no-op ggml_cont in build_sam
- assert num_image_tokens deepseekocr2
- view_seperator as (1, n_embd) at conversion (for both versions)
- drop redundant ggml_reshape_2d

* Update tools/mtmd/models/deepseekocr2.cpp

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>

---------

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
2026-05-29 16:13:51 +02:00
..
batched-bench cmake : add install() for impl libraries + fix apple builds (#23511) 2026-05-22 11:46:26 +03:00
cli app : move licences to llama-app (#23824) 2026-05-29 07:46:11 +02:00
completion app : move licences to llama-app (#23824) 2026-05-29 07:46:11 +02:00
cvector-generator libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
export-lora libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
fit-params cmake : add install() for impl libraries + fix apple builds (#23511) 2026-05-22 11:46:26 +03:00
gguf-split libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
imatrix libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
llama-bench cmake : add install() for impl libraries + fix apple builds (#23511) 2026-05-22 11:46:26 +03:00
mtmd mtmd: Add DeepSeekOCR 2 Support (#20975) 2026-05-29 16:13:51 +02:00
parser libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
perplexity perplexity : fix format specifier in LOG_ERR (#23788) 2026-05-28 10:34:58 +03:00
quantize cmake : add install() for impl libraries + fix apple builds (#23511) 2026-05-22 11:46:26 +03:00
results libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
rpc fix: rpc-server cache may not work in Windows environments (#22394) 2026-04-27 17:25:09 +03:00
server server: bump timeout to 3600s (#23842) 2026-05-29 10:23:17 +02:00
tokenize libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
tts logs : reduce (#23021) 2026-05-14 13:05:52 +03:00
ui ui: fix audio and video modality detection (#23756) 2026-05-28 17:36:10 +02:00
CMakeLists.txt ui: Restructure repo to use tools/ui folder and ui / UI / llama-ui / LLAMA_UI naming (#23064) 2026-05-16 02:02:40 +02:00