mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
e830814399
* 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>
36 lines
1.2 KiB
Python
36 lines
1.2 KiB
Python
# 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.
|
|
|
|
import asyncio
|
|
import importlib
|
|
from typing import Any, Dict
|
|
|
|
from .datatypes import InlineProviderSpec, ProviderSpec, RemoteProviderSpec
|
|
|
|
|
|
def instantiate_class_type(fully_qualified_name):
|
|
module_name, class_name = fully_qualified_name.rsplit(".", 1)
|
|
module = importlib.import_module(module_name)
|
|
return getattr(module, class_name)
|
|
|
|
|
|
# returns a class implementing the protocol corresponding to the Api
|
|
def instantiate_provider(
|
|
provider_spec: InlineProviderSpec,
|
|
provider_config: Dict[str, Any],
|
|
deps: Dict[str, ProviderSpec],
|
|
):
|
|
module = importlib.import_module(provider_spec.module)
|
|
|
|
config_type = instantiate_class_type(provider_spec.config_class)
|
|
config = config_type(**provider_config)
|
|
return asyncio.run(module.get_provider_impl(config, deps))
|
|
|
|
|
|
def instantiate_client(provider_spec: RemoteProviderSpec, base_url: str):
|
|
module = importlib.import_module(provider_spec.module)
|
|
|
|
return asyncio.run(module.get_client_impl(base_url))
|