github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #10060] [CLOSED] Support minicpm omni #59830

New Issue
Closed
opened 2026-04-29 14:45:33 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 14:45:33 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/10060
Author: @tc-mb
Created: 3/31/2025
Status: ❌ Closed

Base: main ← Head: support-minicpm-omni

📝 Commits (10+)

📊 Changes

21 files changed (+11359 additions, -77 deletions)

View changed files

📝 api/types.go (+5 -0)
📝 cmd/cmd.go (+5 -1)
📝 cmd/interactive.go (+140 -43)
📝 cmd/interactive_test.go (+2 -2)
➕ llama/llama.cpp/examples/llava/audio.cpp (+1447 -0)
➕ llama/llama.cpp/examples/llava/audio.h (+48 -0)
➕ llama/llama.cpp/examples/llava/audio_common.cpp (+341 -0)
➕ llama/llama.cpp/examples/llava/audio_common.h (+170 -0)
📝 llama/llama.cpp/examples/llava/clip.cpp (+6 -2)
📝 llama/llama.cpp/examples/llava/clip.h (+2 -1)
➕ llama/llama.cpp/examples/llava/dr_wav.h (+8815 -0)
📝 llama/llama.cpp/examples/llava/llava.cpp (+53 -1)
📝 llama/llama.cpp/examples/llava/llava.h (+4 -0)
📝 llama/llama.go (+84 -0)
📝 llm/server.go (+2 -0)
📝 runner/llamarunner/image.go (+37 -0)
📝 runner/llamarunner/runner.go (+68 -8)
📝 runner/ollamarunner/runner.go (+102 -4)
📝 runner/runner.go (+8 -1)
📝 server/prompt.go (+13 -9)

...and 1 more files

📄 Description

I submitted a PR for omni model capabilities, asking me to modify it with the new engine. I made some preliminary modifications.
#9672
But the new engine has many changes, and some testing may be needed. I see that the design logic of the new engine is different from the previous one, especially it seems that it no longer relies on the backend part of llama.cpp.
This modification of the omni function is completely reproduced by ml, which may be time-consuming. I want to confirm whether to continue to use the backend part of llama.cpp, or whether all new functions need to be implemented with ml?

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/10060 **Author:** [@tc-mb](https://github.com/tc-mb) **Created:** 3/31/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `support-minicpm-omni` --- ### 📝 Commits (10+) - [`6a69927`](https://github.com/ollama/ollama/commit/6a699274516edc3af70a33612157033a85297a3c) fix schema in minicpmv - [`bb2bcb4`](https://github.com/ollama/ollama/commit/bb2bcb43af577230d6d5cd35ffad045e3960c7d9) add video and audio type input - [`c79fb6c`](https://github.com/ollama/ollama/commit/c79fb6c3d99c63a26cc5d169a0777a8dbb750aa7) Merge branch 'main' into support-minicpmo-and-fix-minicpmv - [`3ce5419`](https://github.com/ollama/ollama/commit/3ce541943eb4f5ba59263073f90a574440f03cee) add minicpmv_version - [`65bac73`](https://github.com/ollama/ollama/commit/65bac73daf6a8bee589cad06b55301ffee85225e) fix code - [`62750c2`](https://github.com/ollama/ollama/commit/62750c2d86edc9249eb8a0547430ee7447d24911) update video schema - [`569de8c`](https://github.com/ollama/ollama/commit/569de8c45e1b712ab0d1f307d917f8c7830c40d8) add audio cpp - [`066ba19`](https://github.com/ollama/ollama/commit/066ba190ee903237384cad0ebcdeeceaec241c21) add audio support - [`fb9e95e`](https://github.com/ollama/ollama/commit/fb9e95e8f810daf9d5a39561d80622fc4d2e619a) fix cpp err - [`f577ba5`](https://github.com/ollama/ollama/commit/f577ba525b71a4d8a8c715be691a0479370849eb) fix audio ### 📊 Changes **21 files changed** (+11359 additions, -77 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+5 -0) 📝 `cmd/cmd.go` (+5 -1) 📝 `cmd/interactive.go` (+140 -43) 📝 `cmd/interactive_test.go` (+2 -2) ➕ `llama/llama.cpp/examples/llava/audio.cpp` (+1447 -0) ➕ `llama/llama.cpp/examples/llava/audio.h` (+48 -0) ➕ `llama/llama.cpp/examples/llava/audio_common.cpp` (+341 -0) ➕ `llama/llama.cpp/examples/llava/audio_common.h` (+170 -0) 📝 `llama/llama.cpp/examples/llava/clip.cpp` (+6 -2) 📝 `llama/llama.cpp/examples/llava/clip.h` (+2 -1) ➕ `llama/llama.cpp/examples/llava/dr_wav.h` (+8815 -0) 📝 `llama/llama.cpp/examples/llava/llava.cpp` (+53 -1) 📝 `llama/llama.cpp/examples/llava/llava.h` (+4 -0) 📝 `llama/llama.go` (+84 -0) 📝 `llm/server.go` (+2 -0) 📝 `runner/llamarunner/image.go` (+37 -0) 📝 `runner/llamarunner/runner.go` (+68 -8) 📝 `runner/ollamarunner/runner.go` (+102 -4) 📝 `runner/runner.go` (+8 -1) 📝 `server/prompt.go` (+13 -9) _...and 1 more files_ </details> ### 📄 Description I submitted a PR for omni model capabilities, asking me to modify it with the new engine. I made some preliminary modifications. #9672 But the new engine has many changes, and some testing may be needed. I see that the design logic of the new engine is different from the previous one, especially it seems that it no longer relies on the backend part of llama.cpp. This modification of the omni function is completely reproduced by ml, which may be time-consuming. I want to confirm whether to continue to use the backend part of llama.cpp, or whether all new functions need to be implemented with ml? --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-29 14:45:34 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#59830
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?