 Xuan-Son Nguyen
|
00e3e5a194
mtmd : add qwen2vl and qwen2.5vl (#13141)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
eaea325324
clip : fix model size display (#13153)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
5fa9e63be8
clip : refactor set input for cgraph + fix qwen2.5vl input (#13136)
|
il y a 9 mois |
 LostRuins Concedo
|
59e991c23c
Fixes Qwen2.5VL segfault during inference with https://github.com/ggml-org/llama.cpp/pull/12402 as has_qwen2vl_merger migration was incomplete (#13133)
|
il y a 9 mois |
 HimariO
|
ca2bb89eac
clip : Add Qwen2.5VL support (#12402)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
4753791e70
clip : improve projector naming (#13118)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
edb18b6e8f
clip : fix pixtral on some GPU backends (#13097)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
13be08daf9
clip : remove boi/eoi embeddings for GLM-edge model (#13081)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
ecda2ec4b3
mtmd : Support Pixtral 12B (#13065)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
dc39a5e7a8
mtmd : support SmolVLM (version 1 and 2) (#13050)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
37b9f0d29d
clip : refactor, add `image_manipulation` and `llava_uhd` classes (#13011)
|
il y a 9 mois |
 Matt Clayton
|
e59ea539b8
llava: Fix cpu-only clip image encoding sefault (#12907)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
0c50923944
clip : use smart pointer (⚠️ breaking change) (#12869)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
8b9cc7cdd8
llava : introduce libmtmd (#12849)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
65a69e6e1b
clip : do not print ftype (#12832)
|
il y a 9 mois |
|
Matt Clayton
|
b32efad2bc
llava: improve clip_ctx destructor to not memleak load_image_size (#12834)
|
il y a 9 mois |
 dm4
|
2dabf759e7
llava: add more helper functions to check projector types in clip context (#12824)
|
il y a 9 mois |
|
Xuan-Son Nguyen
|
0364178ca2
clip : refactor clip_init, add tests (#12757)
|
il y a 10 mois |
 Sigbjørn Skjæret
|
1a85949067
llava : proper description fix (#12668)
|
il y a 10 mois |
|
Sigbjørn Skjæret
|
f52d59d771
llava : fix clip loading GGUFs with missing description (#12660)
|
il y a 10 mois |
 Ivy233
|
02082f1519
clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA backend (#12566)
|
il y a 10 mois |
|
Xuan-Son Nguyen
|
7841fc723e
llama : Add Gemma 3 support (+ experimental vision capability) (#12343)
|
il y a 10 mois |
 Xuan-Son Nguyen
|
96e1280839
clip : bring back GPU support (#12322)
|
il y a 10 mois |
 tc-mb
|
8352cdc87b
llava : fix bug in minicpm-v code (#11513)
|
il y a 10 mois |
 Alex Brooks
|
7a2c913e66
llava : Add Granite Vision Support (#11794)
|
il y a 11 mois |
 Ting Lou
|
36c258ee92
llava: build clip image from pixels (#11999)
|
il y a 11 mois |
|
Alex Brooks
|
ee02ad02c5
clip : fix visual encoders with no CLS (#11982)
|
il y a 11 mois |
 SAMI
|
1ec208083c
llava: add quantization for the visual projector LLAVA, Qwen2VL (#11644)
|
il y a 1 an |
 piDack
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
il y a 1 an |
|
tc-mb
|
3e3357fd77
llava : support Minicpm-omni (#11289)
|
il y a 1 an |
