Concedo 4d8a7a6594 fix occasional clip segfault, fix glm4 (+1 squashed commits) ...

Squashed commits:

[bd71cd688] GLM4 fix wip

2025-04-29 01:42:50 +08:00

..

clip-impl.h

Merge branch 'master' into qwen25-vl

2025-04-26 22:45:06 +02:00

clip-quantize-cli.cpp

llava: add quantization for the visual projector LLAVA, Qwen2VL (#11644)

2025-02-05 10:45:40 +03:00

clip.cpp

fix occasional clip segfault, fix glm4 (+1 squashed commits)

2025-04-29 01:42:50 +08:00

clip.h

Merge branch 'upstream' into concedo_experimental

2025-04-27 12:51:02 +08:00

convert_image_encoder_to_gguf.py

llava: add big-endian conversion for image encoder (#12218)

2025-03-06 09:33:21 +01:00

deprecation-warning.cpp

mtmd : merge llava, gemma3 and minicpmv CLI into single llama-mtmd-cli (#13012)

2025-04-21 15:32:58 +02:00

glmedge-convert-image-encoder-to-gguf.py

llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)

2025-02-02 09:48:46 +02:00

glmedge-surgery.py

llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)

2025-02-02 09:48:46 +02:00

llava_surgery_v2.py

Rewrite history to fix bad vulkan shader commits without increasing repo size

2025-03-05 00:02:20 +08:00

llava_surgery.py

py : switch to snake_case (#8305)

2024-07-05 07:53:33 +03:00

llava.cpp

pixtral is working only on cpu, however the images are distorted

2025-04-24 17:59:47 +08:00

llava.h

llava : support MiniCPM-V-2.5 (#7599)

2024-08-09 13:33:53 +03:00

minicpmv-convert-image-encoder-to-gguf.py

llava : fix bug in minicpm-v code (#11513)

2025-03-10 10:33:24 +02:00

minicpmv-surgery.py

llava : support Minicpm-omni (#11289)

2025-01-22 09:35:48 +02:00

mtmd-cli.cpp

arg : add --no-mmproj-offload (#13093)

2025-04-24 14:04:14 +02:00

mtmd.cpp

allow for single token prompt processing (actual batch size 1)

2025-04-25 16:54:46 +08:00

mtmd.h

mtmd : add methods to access mtmd_image_tokens (#12906)

2025-04-18 10:04:51 +02:00

quantclip.cpp

better quant clip

2024-08-18 22:15:59 +08:00

qwen2_vl_surgery.py

remove attn_window_size from gguf

2025-04-26 20:19:51 +08:00

qwen2vl-cli.cpp

remove commented-out code blocks

2025-04-25 22:12:55 +08:00

README-quantize.md

llava: add quantization for the visual projector LLAVA, Qwen2VL (#11644)

2025-02-05 10:45:40 +03:00

requirements.txt

py : fix requirements check '==' -> '~=' (#8982)

2024-08-12 11:02:01 +03:00

test-1.jpeg

clip : refactor clip_init, add tests (#12757)

2025-04-05 17:17:40 +02:00

tests.sh

add test

2025-04-26 23:00:41 +02:00