* fix(embed): use go-rice for large backend assets
Golang embed FS has a hard limit that we might exceed when providing
many binary alternatives.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* simplify golang deps
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): switch to testcontainers and print logs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(tests): do not build a test binary
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* small fixup
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Read jinja templates as fallback
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Move templating out of model loader
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Test TemplateMessages
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Set role and content from transformers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Tests: be more flexible
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* More jinja
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Small refactoring and adaptations
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* specify workdir when launching external backend for safety / relative paths, bump version, logs
Signed-off-by: Dave Lee <dave@gray101.com>
* sneak in a devcontainer fix
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
* minor cleanup to go.mod - importing ourself?
Signed-off-by: Dave Lee <dave@gray101.com>
* figured out why we were importing ourself and fixed it
Signed-off-by: Dave Lee <dave@gray101.com>
* set pull_request_target
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* wip: guess informations from gguf file
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* update go mod
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Small fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Identify llama3
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Do not try to guess the name, as reading gguf files can be expensive
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Allow to disable guessing
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(llama.cpp): Enable decentralized, distributed inference
As https://github.com/mudler/LocalAI/pull/2324 introduced distributed inferencing thanks to
@rgerganov implementation in https://github.com/ggerganov/llama.cpp/pull/6829 in upstream llama.cpp, now
it is possible to distribute the workload to remote llama.cpp gRPC server.
This changeset now uses mudler/edgevpn to establish a secure, distributed network between the nodes using a shared token.
The token is generated automatically when starting the server with the `--p2p` flag, and can be used by starting the workers
with `local-ai worker p2p-llama-cpp-rpc` by passing the token via environment variable (TOKEN) or with args (--token).
As per how mudler/edgevpn works, a network is established between the server and the workers with dht and mdns discovery protocols,
the llama.cpp rpc server is automatically started and exposed to the underlying p2p network so the API server can connect on.
When the HTTP server is started, it will discover the workers in the network and automatically create the port-forwards to the service locally.
Then llama.cpp is configured to use the services.
This feature is behind the "p2p" GO_FLAGS
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* go mod tidy
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: add p2p tag
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* better message
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* auto select cpu variant
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* remove cuda target for now
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* fix metal
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* fix path
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* cuda
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* auto select cuda
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* update test
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* select CUDA backend only if present
Signed-off-by: mudler <mudler@localai.io>
* ci: keep cuda bin in path
Signed-off-by: mudler <mudler@localai.io>
* Makefile: make dist now builds also cuda
Signed-off-by: mudler <mudler@localai.io>
* Keep pushing fallback in case auto-flagset/nvidia fails
There could be other reasons for which the default binary may fail. For example we might have detected an Nvidia GPU,
however the user might not have the drivers/cuda libraries installed in the system, and so it would fail to start.
We keep the fallback of llama.cpp at the end of the llama.cpp backends to try to fallback loading in case things go wrong
Signed-off-by: mudler <mudler@localai.io>
* Do not build cuda on MacOS
Signed-off-by: mudler <mudler@localai.io>
* cleanup
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* Apply suggestions from code review
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: mudler <mudler@localai.io>
