phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-21 17:33:12 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Revert "feat: add batches API with OpenAI compatibility" (#3149)

Browse source 
Reverts llamastack/llama-stack#3088

The PR broke integration tests.
This commit is contained in:
Ashwin Bharambe 2025-08-14 10:08:54 -07:00 • committed by GitHub
parent de692162af
commit ee7631b6cf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 2 additions and 2707 deletions
Download patch file Download diff file Expand all files Collapse all files

40
llama_stack/providers/inline/batches/reference/config.py
View file

@ -1,40 +0,0 @@
# 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.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
class ReferenceBatchesImplConfig(BaseModel):
"""Configuration for the Reference Batches implementation."""
kvstore: KVStoreConfig = 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": SqliteKVStoreConfig.sample_run_config(
__distro_dir__=__distro_dir__,
db_name="batches.db",
),
}