* feat(vllm): build vllm from source for Intel XPU
Upstream publishes no XPU wheels for vllm. The Intel profile was
silently picking up a non-XPU wheel that imported but errored at
engine init, and several runtime deps (pillow, charset-normalizer,
chardet) were missing on Intel -- backend.py crashed at import time
before the gRPC server came up.
Switch the Intel profile to upstream's documented from-source
procedure (docs/getting_started/installation/gpu.xpu.inc.md in
vllm-project/vllm):
- Bump portable Python to 3.12 -- vllm-xpu-kernels ships only a
cp312 wheel.
- Source /opt/intel/oneapi/setvars.sh so vllm's CMake build sees
the dpcpp/sycl compiler from the oneapi-basekit base image.
- Hide requirements-intel-after.txt during installRequirements
(it used to 'pip install vllm'); install vllm's deps from a
fresh git clone of vllm via 'uv pip install -r
requirements/xpu.txt', swap stock triton for
triton-xpu==3.7.0, then 'VLLM_TARGET_DEVICE=xpu uv pip install
--no-deps .'.
- requirements-intel.txt trimmed to LocalAI's direct deps
(accelerate / transformers / bitsandbytes); torch-xpu, vllm,
vllm_xpu_kernels and the rest come from upstream's xpu.txt
during the source build.
- requirements.txt: add pillow + charset-normalizer + chardet --
used by backend.py and missing on the Intel install profile.
- run.sh: 'set -x' so backend startup is visible in container
logs (the gRPC startup error path was previously opaque).
Also adds a one-line docs example for engine_args.attention_backend
under the vLLM section, since older XE-HPG GPUs (e.g. Arc A770)
need TRITON_ATTN to bypass the cutlass path in vllm_xpu_kernels.
Tested end-to-end on an Intel Arc A770 with Qwen2.5-0.5B-Instruct
via LocalAI's /v1/chat/completions.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(vllm): add multi-node data-parallel follower worker
vLLM v1's multi-node story is one process per node sharing a DP
coordinator over ZMQ -- the head runs the API server with
data_parallel_size > 1 and followers run `vllm serve --headless ...`
with matching topology. Today LocalAI can already configure DP on the
head via the engine_args YAML map, but there's no way to bring up the
follower nodes -- so the head sits waiting for ranks that never
handshake.
Add `local-ai p2p-worker vllm`, mirroring MLXDistributed's structural
precedent (operator-launched, static config, no NATS placement). The
worker:
- Optionally self-registers with the frontend as an agent-type node
tagged `node.role=vllm-follower` so it's visible in the admin UI
and operators can scope ordinary models away via inverse
selectors.
- Resolves the platform-specific vllm backend via the gallery's
"vllm" meta-entry (cuda*, intel-vllm, rocm-vllm, ...).
- Runs vLLM as a child process so the heartbeat goroutine survives
until vLLM exits; forwards SIGINT/SIGTERM so vLLM can clean up its
ZMQ sockets before we tear down.
- Validates --headless + --start-rank 0 is rejected (rank 0 is the
head and must serve the API).
Backend run.sh dispatches `serve` as the first arg to vllm's own CLI
instead of LocalAI's backend.py gRPC server -- the follower speaks
ZMQ directly to the head, there is no LocalAI gRPC on the follower
side. Single-node usage is unchanged.
Generalises the gallery resolution helper into findBackendPath()
shared by MLX and vLLM workers; extracts ParseNodeLabels for the
comma-separated label parsing both use.
Ships with two compose recipes (`docker-compose.vllm-multinode.yaml`
for NVIDIA, `docker-compose.vllm-multinode.intel.yaml` for Intel
XPU/xccl) plus `tests/e2e/vllm-multinode/smoke.sh`. Both vendors are
supported (NCCL for CUDA/ROCm, xccl for XPU) but mixed-vendor DP is
not -- PyTorch's process group requires every rank to use the same
collective backend, and NCCL/xccl/gloo don't interoperate.
Out of scope (deferred): SmartRouter-driven placement of follower
ranks via NATS backend.install events, follower log streaming through
/api/backend-logs, tensor-parallel across nodes, disaggregated
prefill via KVTransferConfig.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* test(vllm): CPU-only end-to-end test for multi-node DP
Adds tests/e2e/vllm-multinode/, a Ginkgo + testcontainers-go suite
that brings up a head + headless follower from the locally-built
local-ai:tests image, bind-mounts the cpu-vllm backend extracted by
make extract-backend-vllm so it's seen as a system backend (no gallery
fetch, no registry server), and asserts a chat completion across both
DP ranks. New `make test-e2e-vllm-multinode` target wires the docker
build, backend extract, and ginkgo run together; BuildKit caches both
images so re-runs only rebuild what changed. Tagged Label("VLLMMultinode")
so the existing distributed suite isn't pulled along.
Two pre-existing bugs surfaced by the test:
1. extract-backend-% (Makefile) failed for every backend, because all
backend images end with `FROM scratch` and `docker create` rejects
an image with no CMD/ENTRYPOINT. Fixed by passing
--entrypoint=/run.sh -- the container is never started, only
docker-cp'd, so the path doesn't have to exist; we just need
anything that satisfies the daemon's create-time validation.
2. backend/python/vllm/run.sh's `serve` shortcut for the multi-node DP
follower exec'd ${EDIR}/venv/bin/vllm directly, but uv bakes an
absolute build-time shebang (`#!/vllm/venv/bin/python3`) that no
longer resolves once the backend is relocated to BackendsPath.
_makeVenvPortable's shebang rewriter only matches paths that
already point at ${EDIR}, so the original shebang slips through
unchanged. Fixed by exec-ing ${EDIR}/venv/bin/python with the script
as an argument -- Python ignores the script's shebang in that case.
The test fixture caps memory aggressively (max_model_len=512,
VLLM_CPU_KVCACHE_SPACE=1, TORCH_COMPILE_DISABLE=1) so two CPU engines
fit on a 32 GB box. TORCH_COMPILE_DISABLE is currently mandatory for
cpu-vllm: torch._inductor's CPU-ISA probe runs even with
enforce_eager=True and needs g++ on PATH, which the LocalAI runtime
image doesn't ship -- to be addressed in a follow-up that bundles a
toolchain in the cpu-vllm backend.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(vllm): bundle a g++ toolchain in the cpu-vllm backend image
torch._inductor's CPU-ISA probe (`cpu_model_runner.py:65 "Warming up
model for the compilation"`) shells out to `g++` at vllm engine
startup, regardless of `enforce_eager=True` -- the eager flag only
disables CUDA graphs, not inductor's first-batch warmup. The LocalAI
CPU runtime image (Dockerfile, unconditional apt list) does not ship
build-essential, and the cpu-vllm backend image is `FROM scratch`,
so any non-trivial inference on cpu-vllm crashes with:
torch._inductor.exc.InductorError:
InvalidCxxCompiler: No working C++ compiler found in
torch._inductor.config.cpp.cxx: (None, 'g++')
Bundling the toolchain in the CPU runtime image would bloat every
non-vllm-CPU deployment and force a single GCC version on backends
that may want clang or a different version. So this lives in the
backend, gated to BUILD_TYPE=='' (the CPU profile).
`package.sh` snapshots g++ + binutils + cc1plus + libstdc++ + libc6
(runtime + dev) + the math libs cc1plus links (libisl/libmpc/libmpfr/
libjansson) into ${BACKEND}/toolchain/, mirroring /usr/... layout. The
unversioned binaries on Debian/Ubuntu are symlink chains pointing into
multiarch packages (`g++` -> `g++-13` -> `x86_64-linux-gnu-g++-13`,
the latter in `g++-13-x86-64-linux-gnu`), so the package list resolves
both the version and the arch-triplet variant. Symlinks /lib ->
usr/lib and /lib64 -> usr/lib64 are recreated under the toolchain
root because Ubuntu's UsrMerge keeps them at /, and ld scripts
(`libc.so`, `libm.so`) hardcode `/lib/...` paths that --sysroot
re-roots into the toolchain.
The unversioned `g++`/`gcc`/`cpp` symlinks are replaced with wrapper
shell scripts that resolve their own location at runtime and pass
`--sysroot=<toolchain>` and `-B <toolchain>/usr/lib/gcc/<triplet>/<ver>/`
to the underlying versioned binary. That's how torch's bare `g++ foo.cpp
-o foo` invocation finds cc1plus (-B), system headers (--sysroot), and
the bundled libstdc++ (--sysroot, --sysroot is recursive into linker).
`run.sh` adds the toolchain bin dir to PATH and the toolchain's
shared-lib dir to LD_LIBRARY_PATH -- everything else (header search,
linker search, executable search) is encapsulated in the wrappers.
No-op for non-CPU builds, the dir doesn't exist there.
The cpu-vllm image grows by ~217 MB. Tradeoff is acceptable -- cpu-vllm
is already a niche profile (few users compared to GPU vllm) and the
alternative is a backend that crashes at first inference unless the
operator manually sets TORCH_COMPILE_DISABLE=1, which silently disables
all torch.compile optimizations.
Drops `TORCH_COMPILE_DISABLE=1` from tests/e2e/vllm-multinode -- the
smoke now exercises the real compile path through the bundled toolchain.
Test runtime is +20s for the warmup compile, still <90s end to end.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix(vllm): scope jetson-ai-lab index to L4T-specific wheels via pyproject.toml
The L4T arm64 build resolves dependencies through pypi.jetson-ai-lab.io,
which hosts the L4T-specific torch / vllm / flash-attn wheels but also
transparently proxies the rest of PyPI through `/+f/<sha>/<filename>`
URLs. With `--extra-index-url` + `--index-strategy=unsafe-best-match`
uv would pick those proxy URLs for ordinary PyPI packages —
anthropic/openai/propcache/annotated-types — and fail when the proxy
503s. Master is hitting the same bug on its own l4t-vllm matrix entry.
Switch the l4t13 install path to a pyproject.toml that marks the
jetson-ai-lab index `explicit = true` and pins only torch, torchvision,
torchaudio, flash-attn, and vllm to it via [tool.uv.sources]. uv won't
consult the L4T mirror for anything else, so transitive deps fall back
to PyPI as the default index — no exposure to the proxy 503s.
`uv pip install -r requirements.txt` ignores [tool.uv.sources], so the
l4t13 branch in install.sh now invokes `uv pip install --requirement
pyproject.toml` directly, replacing the old requirements-l4t13*.txt
files. Other BUILD_PROFILEs continue using libbackend.sh's
installRequirements and never read pyproject.toml.
Local resolution test (x86_64, dry-run) confirms uv hits the L4T
index for torch and falls through to PyPI for everything else.
Assisted-by: claude-code:claude-opus-4-7-1m [Read] [Edit] [Bash] [Write]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
- transcript.go: Model not found error now suggests available models commands
- util.go: GGUF error explains format and how to get models
- worker_p2p.go: Token error explains purpose and how to obtain one
- run.go: Startup failure includes troubleshooting steps and docs link
- model_config_loader.go: Config validation errors include file path and guidance
Refs: H2 - UX Review Issue
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(mlx-distributed): add new MLX-distributed backend
Add new MLX distributed backend with support for both TCP and RDMA for
model sharding.
This implementation ties in the discovery implementation already in
place, and re-uses the same P2P mechanism for the TCP MLX-distributed
inferencing.
The Auto-parallel implementation is inspired by Exo's
ones (who have been added to acknowledgement for the great work!)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* expose a CLI to facilitate backend starting
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: make manual rank0 configurable via model configs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add missing features from mlx backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat(loader): refactor single active backend support to LRU
This changeset introduces LRU management of loaded backends. Users can
set now a maximum number of models to be loaded concurrently, and, when
setting LocalAI in single active backend mode we set LRU to 1 for
backward compatibility.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: add tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* More appropriate place for data storing
The /usr/share subtree in Linux is used for data that generally are not
supposed to change. Conventional places for changeable data are usually
located under /var, so /var/lib seems to be a reasonable default here.
* Data paths consistency fix
* Directory name consistency fix
* feat(ui): allow to cancel ops
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Improve progress text
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Cancel queued ops, don't show up message cancellation always
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: fixup displaying of total progress over multiple files
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
- Add a system backend path
- Refactor and consolidate system information in system state
- Use system state in all the components to figure out the system paths
to used whenever needed
- Refactor BackendConfig -> ModelConfig. This was otherway misleading as
now we do have a backend configuration which is not the model config.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
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>
* 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>
* 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>
* fix(p2p): avoid starting the node twice
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(p2p): keep exposing service if we don't start the llama.cpp runner
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* WIP
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Wire up a simple explorer DB
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>
* refactor: group services id so can be identified easily in the ledger table
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(discovery): discovery service now gather worker informations correctly
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(explorer): display network token
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(explorer): display form to add new networks
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(explorer): stop from overwriting networks
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(explorer): display only networks with active workers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(explorer): list only clusters in a network if it has online workers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* remove invalid and inactive networks
if networks have no workers delete them from the database, similarly,
if invalid.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: add workflow to deploy new explorer versions automatically
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* build-api: build with p2p tag
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Allow to specify a connection timeout
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* logging
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Better p2p defaults
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Set loglevel
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fix dht enable
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Default to info for loglevel
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add navbar
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Slightly improve rendering
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Allow to copy the token easily
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
chore: drop gpt4all
gpt4all is already supported in llama.cpp - the backend was kept for
keeping compatibility with old gpt4all models (prior to gguf format).
It is good time now to clean up and remove it to slim the compilation
process.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
feat(p2p): allow to run multiple clusters in the same network
Allow to specify a network ID via CLI which allows to run multiple
clusters, logically separated within the same network (by using the same
shared token).
Note: This segregation is not "secure" by any means, anyone having the
network token can see the services available in all the network,
however, this provides a way to separate the inference endpoints.
This allows for instance to have a node which is both federated and
having attached a set of llama.cpp workers.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Wip p2p enhancements
* get online state
* Pass-by token to show in the dashboard
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Style
* Minor fixups
* parametrize SearchID
* Refactoring
* Allow to expose/bind more services
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add federation
* Display federated mode in the WebUI
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Small fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* make federated nodes visible from the WebUI
* Fix version display
* improve web page
* live page update
* visual enhancements
* enhancements
* visual enhancements
---------
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>
