mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-12-24 15:09:17 -05:00
Code Issues Packages Projects Releases Wiki Activity
4,328 Commits 64 Branches 133 Tags
llama_cpp/shared
Commit Graph

4328 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ettore Di Giacinto
3f52776a1c WIP 2025-07-23 21:18:47 +02:00
Ettore Di Giacinto
5f7ece3e94 fix(p2p): adapt to backend changes, general improvements (#5889) 
The binary is now named "llama-cpp-rpc-server" for p2p workers.

We also decrease the default token rotation interval, in this way
peer discovery is much more responsive.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-23 12:40:32 +02:00
Ettore Di Giacinto
c717b8d800 chore(model gallery): add qwen3-coder-480b-a35b-instruct (#5888) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-23 11:59:58 +02:00
Ettore Di Giacinto
f1d35c4149 chore(model gallery): add qwen3-235b-a22b-instruct-2507 (#5887) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-23 11:54:58 +02:00
Ettore Di Giacinto
ee7e77b6c1 chore(model gallery): add menlo_lucy (#5886) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-23 11:51:51 +02:00
Ettore Di Giacinto
324fecbb75 chore(model gallery): add entfane_math-genius-7b (#5885) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-23 11:45:23 +02:00
Ettore Di Giacinto
a79bfcf0a7 chore(model gallery): add dream-org_dream-v0-instruct-7b (#5884) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-23 11:40:53 +02:00
Ettore Di Giacinto
82495e7fb6 chore(model gallery): add omega-qwen3-atom-8b (#5883) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-23 11:33:43 +02:00
Ettore Di Giacinto
6030b12283 chore(backend gallery): add name to 'diffusers' meta 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-23 09:21:04 +02:00
LocalAI [bot]
b5be867e28 chore: ⬆️ Update ggml-org/llama.cpp to acd6cb1c41676f6bbb25c2a76fa5abeb1719301e (#5882) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-22 21:12:06 +00:00
Ettore Di Giacinto
9b806250d4 chore: drop vllm for cuda 11 (#5881) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-22 18:47:31 +02:00
Ettore Di Giacinto
5f066e702f fix(darwin): add dashes on image suffix 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-22 17:08:19 +02:00
dependabot[bot]
47bb3a3db2 chore(deps): bump securego/gosec from 2.22.5 to 2.22.7 (#5878) 
Bumps [securego/gosec](https://github.com/securego/gosec) from 2.22.5 to 2.22.7.
- [Release notes](https://github.com/securego/gosec/releases)
- [Changelog](https://github.com/securego/gosec/blob/master/.goreleaser.yml)
- [Commits](https://github.com/securego/gosec/compare/v2.22.5...v2.22.7)

---
updated-dependencies:
- dependency-name: securego/gosec
  dependency-version: 2.22.7
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-07-22 16:42:11 +02:00
Richard Palethorpe
51230a801e fix(build): Add and update ONEAPI_VERSION (#5874) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-07-22 16:41:49 +02:00
Richard Palethorpe
754bedc3ea fix(realtime): Reset speech started flag on commit (#5879) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-07-22 16:41:12 +02:00
Ettore Di Giacinto
98e5291afc feat: refactor build process, drop embedded backends (#5875) 
* feat: split remaining backends and drop embedded backends

- Drop silero-vad, huggingface, and stores backend from embedded
  binaries
- Refactor Makefile and Dockerfile to avoid building grpc backends
- Drop golang code that was used to embed backends
- Simplify building by using goreleaser

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(gallery): be specific with llama-cpp backend templates

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(docs): update

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(ci): minor fixes

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: drop all ffmpeg references

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: run protogen-go

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Always enable p2p mode

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Update gorelease file

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(stores): do not always load

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix linting issues

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Mac OS fixup

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-22 16:31:04 +02:00
LocalAI [bot]
e29b2c3aff chore: ⬆️ Update ggml-org/llama.cpp to 6c9ee3b17e19dcc82ab93d52ae46fdd0226d4777 (#5877) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-22 08:25:43 +02:00
LocalAI [bot]
8dc574f3c4 chore: ⬆️ Update ggml-org/whisper.cpp to 1f5cf0b2888402d57bb17b2029b2caa97e5f3baf (#5876) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-22 08:25:13 +02:00
Ettore Di Giacinto
05bf2493a5 fix: do not pass by environ to ffmpeg (#5871) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-21 14:35:33 +02:00
Max Goltzsche
eae4ca08da feat(openai): support input_audio chat api field (#5870) 
Improving the chat completion endpoint OpenAI API compatibility by supporting messages of type `input_audio`, e.g.:
```
{
  ...
  "messages": [
    {
      "role": "user",
      "content": [{
        "type": "input_audio",
        "input_audio": {
          "data": "<base64-encoded audio data>",
          "format": "wav"
        }
      }]
    }
  ]
}
```

Closes #5869

Signed-off-by: Max Goltzsche <max.goltzsche@gmail.com>
 2025-07-21 09:15:55 +02:00
LocalAI [bot]
fa284f7445 chore: ⬆️ Update ggml-org/llama.cpp to 2be60cbc2707359241c2784f9d2e30d8fc7cdabb (#5867) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-21 09:14:09 +02:00
Ettore Di Giacinto
8f69b80520 Update index.yaml 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-07-20 22:54:12 +02:00
Ettore Di Giacinto
b1fc5acd4a feat: split whisper from main binary (#5863) 
* feat: split whisper from main binary

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Cleanup makefile

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add backend builds (missing only darwin)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Test CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add whisper backend to test runs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Make sure we have runtime libs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Less grpc on the main Dockerfile

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix hipblas build

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add whisper to index

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Re-enable CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Adapt auto-bumper

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-20 22:52:45 +02:00
LocalAI [bot]
fab41c29dd chore(model-gallery): ⬆️ update checksum (#5865) 
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-20 20:37:43 +02:00
Ettore Di Giacinto
fb0ec96396 ci: do not upgrade pip 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-20 12:30:12 +02:00
LocalAI [bot]
7659461036 chore: ⬆️ Update ggml-org/llama.cpp to a979ca22db0d737af1e548a73291193655c6be99 (#5862) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-20 08:43:36 +02:00
Ettore Di Giacinto
580687da46 feat: remove stablediffusion-ggml from main binary (#5861) 
* feat: split stablediffusion-ggml from main binary

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Test CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Adapt ci tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Try to support nvidial4t

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Latest fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-19 21:58:53 +02:00
LocalAI [bot]
1929eb2894 chore: ⬆️ Update ggml-org/llama.cpp to bf9087f59aab940cf312b85a67067ce33d9e365a (#5860) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-19 08:52:07 +02:00
Ettore Di Giacinto
b29544d747 feat: split piper from main binary (#5858) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-19 08:31:33 +02:00
Ettore Di Giacinto
7c30e82647 fix: autoload backends when installing models from YAML files (#5859) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-18 21:31:02 +02:00
Dedy F. Setyawan
a1d061c835 fix(docs): Resolve logo overlap on tablet view (#5853) 
* fix(docs): Resolve logo overlap on tablet view

Signed-off-by: Dedy F. Setyawan <dedyfajars@gmail.com>

* fix(docs): Adjust header logo size

Signed-off-by: Dedy F. Setyawan <dedyfajars@gmail.com>

* refactor(docs): Rework header logo sizing implementation

Signed-off-by: Dedy F. Setyawan <dedyfajars@gmail.com>

---------

Signed-off-by: Dedy F. Setyawan <dedyfajars@gmail.com>
 2025-07-18 15:55:44 +02:00
Sijia Lu
851c67019c fix: dockerfile typo (#5823) 
fix dockerfile typo

Signed-off-by: LeonSijiaLu <leonsijialu1@gmail.com>
 2025-07-18 14:59:33 +02:00
Ettore Di Giacinto
53ed5ef189 Makefile fixup 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-18 14:57:14 +02:00
Ettore Di Giacinto
294f7022f3 feat: do not bundle llama-cpp anymore (#5790) 
* Build llama.cpp separately

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* WIP

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* WIP

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* WIP

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Start to try to attach some tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add git and small fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: correctly autoload external backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Try to run AIO tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Slightly update the Makefile helps

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Adapt auto-bumper

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Try to run linux test

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add llama-cpp into build pipelines

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add default capability (for cpu)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Drop llama-cpp specific logic from the backend loader

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* drop grpc install in ci for tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Pass by backends path for tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Build protogen at start

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(tests): set backends path consistently

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Correctly configure the backends path

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Try to build for darwin

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* WIP

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Compile for metal on arm64/darwin

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Try to run build off from cross-arch

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add to the backend index nvidia-l4t and cpu's llama-cpp backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Build also darwin-x86 for llama-cpp

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Disable arm64 builds temporary

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Test backend build on PR

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixup build backend reusable workflow

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* pass by skip drivers

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Use crane

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Skip drivers

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* x86 darwin

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add packaging step for llama.cpp

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix leftover from bark-cpp extraction

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Try to fix hipblas build

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-18 13:24:12 +02:00
Richard Palethorpe
932f6b01a6 feat(realtime): Add speech started and stopped events (#5856) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-07-18 09:22:23 +02:00
LocalAI [bot]
e96452c5d4 chore: ⬆️ Update ggml-org/llama.cpp to d6fb3f6b49b27ef1c0f4cf5128e041f7e7dc03af (#5857) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-17 22:56:40 +00:00
Ettore Di Giacinto
5fc8d5bb78 fix: explorer page should not have login (#5855) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-17 10:54:03 +02:00
LocalAI [bot]
121937ed6f chore: ⬆️ Update ggml-org/llama.cpp to 496957e1cbcb522abc63aa18521036e40efce985 (#5854) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-16 22:52:10 +00:00
LocalAI [bot]
2e38f2a054 chore: ⬆️ Update ggml-org/llama.cpp to 4a4f426944e79b79e389f9ed7b34831cb9b637ad (#5852) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-15 22:56:04 +00:00
LocalAI [bot]
2a6187bc01 chore: ⬆️ Update ggml-org/llama.cpp to bdca38376f7e8dd928defe01ce6a16218a64b040 (#5850) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-15 08:16:01 +02:00
LocalAI [bot]
584c48df5a chore: ⬆️ Update ggml-org/whisper.cpp to 032697b9a850dc2615555e2a93a683cc3dd58559 (#5849) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-14 22:47:30 +00:00
Ettore Di Giacinto
8dd67748a1 chore(model gallery): add sophosympatheia_strawberrylemonade-70b-v1.1 (#5848) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-14 15:38:41 +02:00
Ettore Di Giacinto
3fd0bf3c88 chore(model gallery): add zhi-create-qwen3-32b-i1 (#5847) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-14 15:33:40 +02:00
LocalAI [bot]
4062a6c404 chore: ⬆️ Update ggml-org/llama.cpp to 982e347255723fe6d02e60ee30cfdd0559c884c5 (#5845) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-14 08:21:54 +02:00
Ettore Di Giacinto
354c0b763e feat(cli): add command to create custom OCI images from directories (#5844) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-14 08:21:29 +02:00
LocalAI [bot]
40f9065367 chore: ⬆️ Update ggml-org/whisper.cpp to a16da91365700f396da916d16a7f5a2ec99364b9 (#5846) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-13 22:46:03 +00:00
Ettore Di Giacinto
fc02bc0aba chore(model gallery): add google_medgemma-27b-it (#5843) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-13 18:20:21 +02:00
Ettore Di Giacinto
45badb75e8 chore(model gallery): add google_medgemma-4b-it (#5842) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-13 17:56:44 +02:00
LocalAI [bot]
d7e1922582 chore: ⬆️ Update ggml-org/whisper.cpp to 3775c503d5133d3d8b99d7d062e87a54064b0eb8 (#5841) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-13 08:49:15 +02:00
LocalAI [bot]
642a39afa0 chore: ⬆️ Update ggml-org/llama.cpp to c31e60647def83d671bac5ab5b35579bf25d9aa1 (#5840) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-12 22:44:45 +00:00