chore(package): migrate to src/ layout (#3920)

Migrates package structure to src/ layout following Python packaging
best practices.

All code moved from `llama_stack/` to `src/llama_stack/`. Public API
unchanged - imports remain `import llama_stack.*`.

Updated build configs, pre-commit hooks, scripts, and GitHub workflows
accordingly. All hooks pass, package builds cleanly.

**Developer note**: Reinstall after pulling: `pip install -e .`
This commit is contained in:
Ashwin Bharambe 2025-10-27 12:02:21 -07:00 committed by GitHub
parent 98a5047f9d
commit 471b1b248b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
791 changed files with 2983 additions and 456 deletions

View file

@ -0,0 +1,40 @@
# 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 pydantic import BaseModel, Field
from llama_stack.core.storage.datatypes import KVStoreReference
class ReferenceBatchesImplConfig(BaseModel):
"""Configuration for the Reference Batches implementation."""
kvstore: KVStoreReference = Field(
description="Configuration for the key-value store backend.",
)
max_concurrent_batches: int = Field(
default=1,
description="Maximum number of concurrent batches to process simultaneously.",
ge=1,
)
max_concurrent_requests_per_batch: int = Field(
default=10,
description="Maximum number of concurrent requests to process per batch.",
ge=1,
)
# TODO: add a max requests per second rate limiter
@classmethod
def sample_run_config(cls, __distro_dir__: str) -> dict:
return {
"kvstore": KVStoreReference(
backend="kv_default",
namespace="batches",
).model_dump(exclude_none=True),
}