 Xuan-Son Nguyen
|
edb18b6e8f
clip : fix pixtral on some GPU backends (#13097)
|
8 月之前 |
|
Xuan-Son Nguyen
|
13be08daf9
clip : remove boi/eoi embeddings for GLM-edge model (#13081)
|
8 月之前 |
|
Xuan-Son Nguyen
|
ecda2ec4b3
mtmd : Support Pixtral 12B (#13065)
|
8 月之前 |
|
Xuan-Son Nguyen
|
dc39a5e7a8
mtmd : support SmolVLM (version 1 and 2) (#13050)
|
9 月之前 |
|
Xuan-Son Nguyen
|
37b9f0d29d
clip : refactor, add `image_manipulation` and `llava_uhd` classes (#13011)
|
9 月之前 |
 Matt Clayton
|
e59ea539b8
llava: Fix cpu-only clip image encoding sefault (#12907)
|
9 月之前 |
|
Xuan-Son Nguyen
|
0c50923944
clip : use smart pointer (⚠️ breaking change) (#12869)
|
9 月之前 |
|
Xuan-Son Nguyen
|
8b9cc7cdd8
llava : introduce libmtmd (#12849)
|
9 月之前 |
|
Xuan-Son Nguyen
|
65a69e6e1b
clip : do not print ftype (#12832)
|
9 月之前 |
|
Matt Clayton
|
b32efad2bc
llava: improve clip_ctx destructor to not memleak load_image_size (#12834)
|
9 月之前 |
 dm4
|
2dabf759e7
llava: add more helper functions to check projector types in clip context (#12824)
|
9 月之前 |
|
Xuan-Son Nguyen
|
0364178ca2
clip : refactor clip_init, add tests (#12757)
|
9 月之前 |
 Sigbjørn Skjæret
|
1a85949067
llava : proper description fix (#12668)
|
9 月之前 |
|
Sigbjørn Skjæret
|
f52d59d771
llava : fix clip loading GGUFs with missing description (#12660)
|
9 月之前 |
 Ivy233
|
02082f1519
clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA backend (#12566)
|
9 月之前 |
|
Xuan-Son Nguyen
|
7841fc723e
llama : Add Gemma 3 support (+ experimental vision capability) (#12343)
|
10 月之前 |
 Xuan-Son Nguyen
|
96e1280839
clip : bring back GPU support (#12322)
|
10 月之前 |
 tc-mb
|
8352cdc87b
llava : fix bug in minicpm-v code (#11513)
|
10 月之前 |
 Alex Brooks
|
7a2c913e66
llava : Add Granite Vision Support (#11794)
|
10 月之前 |
 Ting Lou
|
36c258ee92
llava: build clip image from pixels (#11999)
|
10 月之前 |
|
Alex Brooks
|
ee02ad02c5
clip : fix visual encoders with no CLS (#11982)
|
11 月之前 |
 SAMI
|
1ec208083c
llava: add quantization for the visual projector LLAVA, Qwen2VL (#11644)
|
11 月之前 |
 piDack
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
11 月之前 |
|
tc-mb
|
3e3357fd77
llava : support Minicpm-omni (#11289)
|
1 年之前 |
 Johannes Gäßler
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 年之前 |
 Georgi Gerganov
|
d408bb9268
clip : disable GPU support (#10896)
|
1 年之前 |
|
Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 年之前 |
 HimariO
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 年之前 |
|
piDack
|
01e6d9bb71
clip : add sycl support (#10574)
|
1 年之前 |
 Ting Lou
|
678d7994f4
llava: return false instead of exit (#10546)
|
1 年之前 |
