forked from phoenix-oss/llama-stack-mirror
9487ad8294
* API Keys passed from Client instead of distro configuration * delete distribution registry * Rename the "package" word away * Introduce a "Router" layer for providers Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. * update `apis_to_serve` * llama_toolchain -> llama_stack * Codemod from llama_toolchain -> llama_stack - added providers/registry - cleaned up api/ subdirectories and moved impls away - restructured api/api.py - from llama_stack.apis.<api> import foo should work now - update imports to do llama_stack.apis.<api> - update many other imports - added __init__, fixed some registry imports - updated registry imports - create_agentic_system -> create_agent - AgenticSystem -> Agent * Moved some stuff out of common/; re-generated OpenAPI spec * llama-toolchain -> llama-stack (hyphens) * add control plane API * add redis adapter + sqlite provider * move core -> distribution * Some more toolchain -> stack changes * small naming shenanigans * Removing custom tool and agent utilities and moving them client side * Move control plane to distribution server for now * Remove control plane from API list * no codeshield dependency randomly plzzzzz * Add "fire" as a dependency * add back event loggers * stack configure fixes * use brave instead of bing in the example client * add init file so it gets packaged * add init files so it gets packaged * Update MANIFEST * bug fix --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Xi Yan <xiyan@meta.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
57 lines
1.8 KiB
Python
57 lines
1.8 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.
|
|
|
|
from typing import Optional
|
|
|
|
from llama_models.datatypes import ModelFamily
|
|
|
|
from llama_models.schema_utils import json_schema_type
|
|
from llama_models.sku_list import all_registered_models, resolve_model
|
|
|
|
from llama_stack.apis.inference import QuantizationConfig
|
|
|
|
from pydantic import BaseModel, Field, field_validator
|
|
|
|
|
|
@json_schema_type
|
|
class MetaReferenceImplConfig(BaseModel):
|
|
model: str = Field(
|
|
default="Meta-Llama3.1-8B-Instruct",
|
|
description="Model descriptor from `llama model list`",
|
|
)
|
|
quantization: Optional[QuantizationConfig] = None
|
|
torch_seed: Optional[int] = None
|
|
max_seq_len: int
|
|
max_batch_size: int = 1
|
|
|
|
@field_validator("model")
|
|
@classmethod
|
|
def validate_model(cls, model: str) -> str:
|
|
permitted_models = [
|
|
m.descriptor()
|
|
for m in all_registered_models()
|
|
if m.model_family == ModelFamily.llama3_1
|
|
]
|
|
if model not in permitted_models:
|
|
model_list = "\n\t".join(permitted_models)
|
|
raise ValueError(
|
|
f"Unknown model: `{model}`. Choose from [\n\t{model_list}\n]"
|
|
)
|
|
return model
|
|
|
|
@property
|
|
def model_parallel_size(self) -> int:
|
|
# HUGE HACK ALERT: this will be fixed when we move inference configuration
|
|
# to ModelsRegistry and we can explicitly ask for `model_parallel_size`
|
|
# as configuration there
|
|
gpu_count = 1
|
|
resolved = resolve_model(self.model)
|
|
assert resolved is not None
|
|
descriptor = resolved.descriptor().lower()
|
|
if "-70b" in descriptor or "-405b" in descriptor:
|
|
gpu_count = 8
|
|
|
|
return gpu_count
|