Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[pull] master from mudler:master #73

Merged
merged 91 commits into from
May 13, 2024
Merged

[pull] master from mudler:master #73

merged 91 commits into from
May 13, 2024

Conversation

pull[bot]
Copy link

@pull pull bot commented May 2, 2024

See Commits and Changes for more details.


Created by pull[bot]

Can you help keep this open source service alive? 💖 Please sponsor : )

mudler and others added 2 commits May 1, 2024 23:06
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
user defined inference device

configuration via main_gpu parameter
@pull pull bot added ⤵️ pull and removed area/ai-model labels May 2, 2024
mudler and others added 5 commits May 2, 2024 21:14
* feat(webui): Add chat page

Signed-off-by: Ettore Di Giacinto <[email protected]>

* feat(webui): Add image-gen page

Signed-off-by: Ettore Di Giacinto <[email protected]>

* feat(webui): Add tts page

Signed-off-by: Ettore Di Giacinto <[email protected]>

---------

Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
* feat(ui/chat): handle multiline in the input field

Signed-off-by: mudler <[email protected]>

* feat(ui/chat): correctly display multiline messages

Signed-off-by: mudler <[email protected]>

* feat(ui/chat): add list style

Signed-off-by: mudler <[email protected]>

---------

Signed-off-by: mudler <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
cryptk and others added 15 commits May 3, 2024 18:46
* feat: update ROCM and use smaller image

Signed-off-by: Chris Jowett <[email protected]>

* fix: add call to ldconfig to fix AMDs broken library packages

Signed-off-by: Chris Jowett <[email protected]>

---------

Signed-off-by: Chris Jowett <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
…angchainpy-localai-example in the pip group across 1 directory (#2231)

build(deps): bump tqdm

Bumps the pip group with 1 update in the /examples/langchain/langchainpy-localai-example directory: [tqdm](https://github.com/tqdm/tqdm).


Updates `tqdm` from 4.65.0 to 4.66.3
- [Release notes](https://github.com/tqdm/tqdm/releases)
- [Commits](tqdm/tqdm@v4.65.0...v4.66.3)

---
updated-dependencies:
- dependency-name: tqdm
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
…p variants (#2232)

* feat(initializer): do not specify backends to autoload

We can simply try to autoload the backends extracted in the asset dir.
This will allow to build variants of the same backend (for e.g. with different instructions sets),
so to have a single binary for all the variants.

Signed-off-by: mudler <[email protected]>

* refactor(prepare): refactor out llama.cpp prepare steps

Make it so are idempotent and that we can re-build

Signed-off-by: mudler <[email protected]>

* [TEST] feat(build): build noavx version along

Signed-off-by: mudler <[email protected]>

* build: make build parallel

Signed-off-by: Ettore Di Giacinto <[email protected]>

* build: do not override CMAKE_ARGS

Signed-off-by: Ettore Di Giacinto <[email protected]>

* build: add fallback variant

Signed-off-by: Ettore Di Giacinto <[email protected]>

* Fixups

Signed-off-by: Ettore Di Giacinto <[email protected]>

* fix(huggingface-langchain): fail if no token is set

Signed-off-by: Ettore Di Giacinto <[email protected]>

* fix(huggingface-langchain): rename

Signed-off-by: Ettore Di Giacinto <[email protected]>

* fix: do not autoload local-store

Signed-off-by: Ettore Di Giacinto <[email protected]>

* fix: give priority between the listed backends

Signed-off-by: Ettore Di Giacinto <[email protected]>

---------

Signed-off-by: mudler <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
fix(gallery): hermes-2-pro-llama3 models checksum

Signed-off-by: Gerrit Pannek <[email protected]>
* models(gallery): add moondream2

Signed-off-by: Ettore Di Giacinto <[email protected]>

* models(gallery): fix typo for TTS models

Signed-off-by: Ettore Di Giacinto <[email protected]>

* models(gallery): add base config for moondream2 and icon

Signed-off-by: Ettore Di Giacinto <[email protected]>

* linter fixes

Signed-off-by: Ettore Di Giacinto <[email protected]>

---------

Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
mudler and others added 29 commits May 9, 2024 00:54
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
* feat: migrate diffusers backend from conda to uv

  - replace conda with UV for diffusers install (prototype for all
    extras backends)
  - add ability to build docker with one/some/all extras backends
    instead of all or nothing

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate autogtpq bark coqui from conda to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: convert exllama over to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate exllama2 to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate mamba to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate parler to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate petals to uv

Signed-off-by: Chris Jowett <[email protected]>

* fix: fix tests

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate rerankers to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate sentencetransformers to uv

Signed-off-by: Chris Jowett <[email protected]>

* fix: install uv for tests-linux

Signed-off-by: Chris Jowett <[email protected]>

* fix: make sure file exists before installing on intel images

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate transformers backend to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate transformers-musicgen to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate vall-e-x to uv

Signed-off-by: Chris Jowett <[email protected]>

* feat: migrate vllm to uv

Signed-off-by: Chris Jowett <[email protected]>

* fix: add uv install to the rest of test-extra.yml

Signed-off-by: Chris Jowett <[email protected]>

* fix: adjust file perms on all install/run/test scripts

Signed-off-by: Chris Jowett <[email protected]>

* fix: add missing acclerate dependencies

Signed-off-by: Chris Jowett <[email protected]>

* fix: add some more missing dependencies to python backends

Signed-off-by: Chris Jowett <[email protected]>

* fix: parler tests venv py dir fix

Signed-off-by: Chris Jowett <[email protected]>

* fix: correct filename for transformers-musicgen tests

Signed-off-by: Chris Jowett <[email protected]>

* fix: adjust the pwd for valle tests

Signed-off-by: Chris Jowett <[email protected]>

* feat: cleanup and optimization work for uv migration

Signed-off-by: Chris Jowett <[email protected]>

* fix: add setuptools to requirements-install for mamba

Signed-off-by: Chris Jowett <[email protected]>

* feat: more size optimization work

Signed-off-by: Chris Jowett <[email protected]>

* feat: make installs and tests more consistent, cleanup some deps

Signed-off-by: Chris Jowett <[email protected]>

* fix: cleanup

Signed-off-by: Chris Jowett <[email protected]>

* fix: mamba backend is cublas only

Signed-off-by: Chris Jowett <[email protected]>

* fix: uncomment lines in makefile

Signed-off-by: Chris Jowett <[email protected]>

---------

Signed-off-by: Chris Jowett <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
…ds (#2286)

* feat: create bash library to handle install/run/test of python backends

Signed-off-by: Chris Jowett <[email protected]>

* chore: minor cleanup

Signed-off-by: Chris Jowett <[email protected]>

* fix: remove incorrect LIMIT_TARGETS from parler-tts

Signed-off-by: Chris Jowett <[email protected]>

* fix: update runUnitests to handle running tests from a custom test file

Signed-off-by: Chris Jowett <[email protected]>

* chore: document runUnittests

Signed-off-by: Chris Jowett <[email protected]>

---------

Signed-off-by: Chris Jowett <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
When enabling grammar with functions, it might be useful to
allow more flexibility to support models that are fine-tuned against returning
function calls of the form of { "name": "function_name", "arguments" {...} }
rather then { "function": "function_name", "arguments": {..} }.

This might call out to a more generic approach later on, but for the moment being we can easily support both
as we have just to specific different types.

If needed we can expand on this later on

Signed-off-by: mudler <[email protected]>
seperate -> separate

Signed-off-by: Ikko Eltociear Ashimine <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <[email protected]>
@pull pull bot merged commit b4cb22f into kp-forks:master May 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

9 participants