[swift] add module omnivlm #11171

Closed

TerryT9 wants to merge 80 commits intoggml-org:masterfrom

NexaAI:t/omnivlm-ios

Commits on Sep 10, 2024

Commits on Oct 23, 2024

update vulkan target name
zhiyuan8
committed

Commits on Nov 6, 2024

add returned string (pure c const char* type) for omni-vlm inference api

李为
authored and
李为
committed
Merge pull request #10 from NexaAI/weili/master-release
zhiyuan8
authored
add returned string (const char*) for qwen2 audio

李为
authored and
李为
committed
Merge pull request #11 from NexaAI/weili/master-release
zhiyuan8
authored

Commits on Nov 7, 2024

add returned string type (const char*) for nexa-omni-audio

李为
authored and
李为
committed
Merge pull request #12 from NexaAI/weili/master-release
zhiyuan8
authored
add returned string type (const char*) for nexa-omni-audio

李为
authored and
李为
committed
Merge pull request #13 from NexaAI/weili/master-release
zhiyuan8
authored

Commits on Nov 8, 2024

add submodule llava for android
liute110
committed
add one more model
liute110
committed
add include llava.h
liute110
committed
remove redundant omni-vlm-v2/ folder, all omni-vlm examples will be added to omni-vlm/ folder.

李为
authored and
李为
committed
remove omni-vlm-v2/

李为
authored and
李为
committed
update README.md

李为
authored and
李为
committed
Merge pull request #15 from NexaAI/weili/master-release
zhiyuan8
authored
Merge pull request #14 from NexaAI/teliu/android/dev
zhiyuan8
authored
changed download models and nlen
zhycheng614
committed
Merge pull request #16 from NexaAI/perry/android-dev
zhycheng614
authored

Commits on Nov 9, 2024

fix OCR template error.

李为
authored and
李为
committed
Merge pull request #17 from NexaAI/weili/master-release
zhiyuan8
authored

Commits on Nov 10, 2024

Create CODEOWNERS
zhiyuan8
authored

Commits on Nov 11, 2024

reset model in every inerence step to avoid nosense output.

李为
authored and
李为
committed
Merge pull request #18 from NexaAI/weili/master-release
zhiyuan8
authored
Merge pull request #19 from NexaAI/master
zhiyuan8
authored

Commits on Nov 14, 2024

[memory leakage] fixed a leakage by projector free

李为
authored and
李为
committed
Merge pull request #24 from NexaAI/weili/master-release
zhiyuan8
authored
audio embedding free() (but still memory leakage detected)

李为
authored and
李为
committed
fix mem leakage based on leaks tool (still WIP)

李为
authored and
李为
committed

Commits on Nov 15, 2024

free omni_ctx heap malloc space in omni_free() api

李为
authored and
李为
committed
Merge pull request #25 from NexaAI/weili/master-release
zhiyuan8
authored
Merge pull request #26 from NexaAI/master
zhiyuan8
authored

Commits on Nov 21, 2024

remove reference interface from extern C in qwen2audio examples

李为
authored and
李为
committed
expose omni_context_params struct

李为
authored and
李为
committed

Commits on Dec 3, 2024

Merge branch 'weili/dev' of github.com:NexaAI/llama.cpp into weili/dev

李为
authored and
李为
committed
bug fix in common-nexa.cpp
liwiii
authored
bug fix

李为
authored and
李为
committed
fix clip_n_patch() allocation size error for 81-series omni-vlm models

李为
authored and
李为
committed
Merge branch 'weili/dev' of github.com:NexaAI/llama.cpp into weili/dev

李为
authored and
李为
committed
remove iostream header

李为
authored and
李为
committed
Merge pull request #33 from NexaAI/weili/dev
zhiyuan8
authored
update omni audio cmake
TerryT9
committed

Commits on Dec 10, 2024

Update omni-audio cmake content to make it static (#36)
TerryT9
authored

Commits on Jan 6, 2025

Add streaming for omnivlm (#39)
TerryT9
authored

Commits on Jan 10, 2025