GitLab

Bump llama.cpp to b2510

Integration tests conditionally pull

Add support for libcudart.so for CUDA devices (Adds Jetson support)

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* Update README.md

* Update README.md

---------
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Dify.AI is a model-agnostic LLMOps platform for building and managing LLM applications.
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* Update README.md

* Update README.md

---------
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Added Ollama Basic chat based on hyperdiv
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

adding drazdra/ollama-chats to the list of UI :)

If images aren't present, pull them.
Also fixes the expected responses

Add docs for GPU selection and nvidia uvm workaround

Testcontainers provides a module for Ollama.

Revamp go based integration tests

This uplevels the integration tests to run the server which can allow
testing an existing server, or a remote server.

The release just before ggml-cuda.cu refactoring

Better tmpdir cleanup

If expanding the runners fails, don't leave a corrupt/incomplete payloads dir
We now write a pid file out to the tmpdir, which allows us to scan for stale tmpdirs
and remove this as long as there isn't still a process running.

remove global

refactor readseeker