Introduce Llama stack distributions (#22)

* Add distribution CLI scaffolding

* More progress towards `llama distribution install`

* getting closer to a distro definition, distro install + configure works

* Distribution server now functioning

* read existing configuration, save enums properly

* Remove inference uvicorn server entrypoint and llama inference CLI command

* updated dependency and client model name

* Improved exception handling

* local imports for faster cli

* undo a typo, add a passthrough distribution

* implement full-passthrough in the server

* add safety adapters, configuration handling, server + clients

* cleanup, moving stuff to common, nuke utils

* Add a Path() wrapper at the earliest place

* fixes

* Bring agentic system api to toolchain

Add adapter dependencies and resolve adapters using a topological sort

* refactor to reduce size of `agentic_system`

* move straggler files and fix some important existing bugs

* ApiSurface -> Api

* refactor a method out

* Adapter -> Provider

* Make each inference provider into its own subdirectory

* installation fixes

* Rename Distribution -> DistributionSpec, simplify RemoteProviders

* dict key instead of attr

* update inference config to take model and not model_dir

* Fix passthrough streaming, send headers properly not part of body :facepalm

* update safety to use model sku ids and not model dirs

* Update cli_reference.md

* minor fixes

* add DistributionConfig, fix a bug in model download

* Make install + start scripts do proper configuration automatically

* Update CLI_reference

* Nuke fp8_requirements, fold fbgemm into common requirements

* Update README, add newline between API surface configurations

* Refactor download functionality out of the Command so can be reused

* Add `llama model download` alias for `llama download`

* Show message about checksum file so users can check themselves

* Simpler intro statements

* get ollama working

* Reduce a bunch of dependencies from toolchain

Some improvements to the distribution install script

* Avoid using `conda run` since it buffers everything

* update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes

* add validation for configuration input

* resort imports

* make optional subclasses default to yes for configuration

* Remove additional_pip_packages; move deps to providers

* for inline make 8b model the default

* Add scripts to MANIFEST

* allow installing from test.pypi.org

* Fix #2 to help with testing packages

* Must install llama-models at that same version first

* fix PIP_ARGS

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Hardik Shah <hjshah@meta.com>

llama_toolchain/distribution/registry.py

@@ -0,0 +1,61 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from functools import lru_cache
+from typing import List, Optional
+
+from .datatypes import Api, DistributionSpec, RemoteProviderSpec
+from .distribution import api_providers
+
+
+def client_module(api: Api) -> str:
+    return f"llama_toolchain.{api.value}.client"
+
+
+def remote_spec(api: Api) -> RemoteProviderSpec:
+    return RemoteProviderSpec(
+        api=api,
+        provider_id=f"{api.value}-remote",
+        module=client_module(api),
+    )
+
+
+@lru_cache()
+def available_distribution_specs() -> List[DistributionSpec]:
+    providers = api_providers()
+    return [
+        DistributionSpec(
+            spec_id="inline",
+            description="Use code from `llama_toolchain` itself to serve all llama stack APIs",
+            provider_specs={
+                Api.inference: providers[Api.inference]["meta-reference"],
+                Api.safety: providers[Api.safety]["meta-reference"],
+                Api.agentic_system: providers[Api.agentic_system]["meta-reference"],
+            },
+        ),
+        DistributionSpec(
+            spec_id="remote",
+            description="Point to remote services for all llama stack APIs",
+            provider_specs={x: remote_spec(x) for x in providers},
+        ),
+        DistributionSpec(
+            spec_id="ollama-inline",
+            description="Like local-source, but use ollama for running LLM inference",
+            provider_specs={
+                Api.inference: providers[Api.inference]["meta-ollama"],
+                Api.safety: providers[Api.safety]["meta-reference"],
+                Api.agentic_system: providers[Api.agentic_system]["meta-reference"],
+            },
+        ),
+    ]
+
+
+@lru_cache()
+def resolve_distribution_spec(spec_id: str) -> Optional[DistributionSpec]:
+    for spec in available_distribution_specs():
+        if spec.spec_id == spec_id:
+            return spec
+    return None