COMMITS
/ tools/mtmd/clip.cpp April 2, 2026
X
model, mtmd: fix gguf conversion for audio/vision mmproj (#21309)
Xuan-Son Nguyen committed
March 27, 2026
X
mtmd: add more sanity checks (#21047)
Xuan-Son Nguyen committed
March 26, 2026
X
mtmd: refactor image preprocessing (#21031)
Xuan-Son Nguyen committed
March 25, 2026
S
mtmd: Add DeepSeekOCR Support (#17400)
Saba Fallah committed
March 23, 2026
B
D
mtmd : fix LightOnOCR image preprocessing (#20877)
DorianRudolph committed
March 19, 2026
X
mtmd: add clip_graph::build_mm() (#20751)
Xuan-Son Nguyen committed
March 14, 2026
X
mtmd: add llama-mtmd-debug binary (#20508)
Xuan-Son Nguyen committed
March 11, 2026
D
model : add support for Phi4ForCausalLMV (#20168)
DAN™ committed
March 5, 2026
M
chore : correct typos [no ci] (#20041)
Marcel Petrick committed
February 19, 2026
M
model: Add PaddleOCR-VL model support (#18825)
megemini committed
S
mtmd: build_attn modified, flash_attn on/off via ctx_params (#19729)
Saba Fallah committed
February 18, 2026
X
model: support GLM-OCR (#19677)
Xuan-Son Nguyen committed
February 14, 2026
A
mtmd : Add Nemotron Nano 12B v2 VL support (#19547)
Anav Prasad committed
February 11, 2026
A
model: Add Kimi-K2.5 support (#19170)
AesSedai committed
February 9, 2026
T
mtmd: Implement tiling for LFM2-VL (#19454)
Tarek Dakhran committed
January 30, 2026
T
mtmd: support MiniCPM-o 4.5(vision only) (#19211)
tc-mb committed
January 14, 2026
P
Restore clip's cb() to its rightful glory - extract common debugging elements in llama (#17914)
Piotr Wilkin (ilintar) committed
January 13, 2026
X
mtmd: fix use_non_causal being reported incorrectly (#18793)
Xuan-Son Nguyen committed
January 9, 2026
S
mtmd: Add Gemma3n multimodal support with MobileNetV5 vision encoder (#18256)
Simranjeet Singh committed
January 4, 2026
T
model : mtmd : make input norm optional in LFM2-VL (#18594)
Tarek Dakhran committed
January 1, 2026
T
model: support youtu-vl model (#18479)
tt committed
December 31, 2025
H
mtmd : Adding support for Nvidia Music Flamingo Model (#18470)
Henry147147 committed
December 18, 2025
X
model : add ASR support for LFM2-Audio-1.5B (conformer) (#18106)
Xuan-Son Nguyen committed
December 16, 2025
X
model: support GLM4V vision encoder (#18042)
Xuan-Son Nguyen committed
December 15, 2025
X
mtmd: refactor audio preprocessing (#17978)
Xuan-Son Nguyen committed
P
model : add glm-asr support (#17901)
piDack committed
December 14, 2025
H
mtmd: enhance image resizing in llava_uhd (#18014)
Haowei Wu committed
December 12, 2025
X
clip: move model cgraphs into their own files (#17965)
Xuan-Son Nguyen committed
December 10, 2025
X
mtmd: some small clean up (#17909)
Xuan-Son Nguyen committed
G
ggml : remove GGML_KQ_MASK_PAD constant (#17910)
Georgi Gerganov committed
December 2, 2025
X
mtmd: fix --no-warmup (#17695)
Xuan-Son Nguyen committed
December 1, 2025
X
mtmd: add mtmd_context_params::warmup option (#17652)
Xuan-Son Nguyen committed
November 30, 2025
T
model: LFM2-VL fixes (#17577)
Tarek Dakhran committed
X
clip: fix nb calculation for qwen3-vl (#17594)
Xuan-Son Nguyen committed
November 26, 2025
H
clip: (minicpmv) fix resampler kq_scale (#17516)
Han Qingzhe committed
November 14, 2025
X
mtmd: add mtmd_log_set (#17268)
Xuan-Son Nguyen committed
November 10, 2025
X
mtmd: fix patch_size initialized to random value in audio models (#17128)
Xuan-Son Nguyen committed
November 6, 2025
X
clip: implement minicpm-v sinusoidal embd using GGML (#17036)
Xuan-Son Nguyen committed
November 5, 2025
X
mtmd: allow QwenVL to process larger image by default (#17020)
Xuan-Son Nguyen committed
X
mtmd: improve struct initialization (#16981)
Xuan-Son Nguyen committed
November 3, 2025
X
mtmd: add --image-min/max-tokens (#16921)
Xuan-Son Nguyen committed
X
mtmd: pad mask for qwen2.5vl (#16954)
Xuan-Son Nguyen committed
November 2, 2025
Z
model: add Janus Pro for image understanding (#16906)
Zhiyong Wang committed
G
clip : use FA (#16837)
Georgi Gerganov committed
November 1, 2025
X
mtmd: refactor preprocessing + support max/min pixels (#16878)
Xuan-Son Nguyen committed
October 30, 2025
J
model: add support for qwen3vl series (#16780)
JJJYmmm committed
T
model: Add support for CogVLM model (#15002)
Tianyue-Zhao committed
October 27, 2025
X
mtmd : fix idefics3 preprocessing (#16806)
Xuan-Son Nguyen committed
X
model : add LightOnOCR-1B model (#16764)
Xuan-Son Nguyen committed