Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
41 lines
1.2 KiB
Python
41 lines
1.2 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from functools import lru_cache
|
|
from pathlib import Path
|
|
|
|
import vllm.envs as envs
|
|
from vllm.connections import global_http_connection
|
|
|
|
VLLM_S3_BUCKET_URL = "https://vllm-public-assets.s3.us-west-2.amazonaws.com"
|
|
|
|
|
|
def get_cache_dir() -> Path:
|
|
"""Get the path to the cache for storing downloaded assets."""
|
|
path = Path(envs.VLLM_ASSETS_CACHE)
|
|
path.mkdir(parents=True, exist_ok=True)
|
|
|
|
return path
|
|
|
|
|
|
@lru_cache
|
|
def get_vllm_public_assets(filename: str, s3_prefix: str | None = None) -> Path:
|
|
"""
|
|
Download an asset file from `s3://vllm-public-assets`
|
|
and return the path to the downloaded file.
|
|
"""
|
|
asset_directory = get_cache_dir() / "vllm_public_assets"
|
|
asset_directory.mkdir(parents=True, exist_ok=True)
|
|
|
|
asset_path = asset_directory / filename
|
|
if not asset_path.exists():
|
|
if s3_prefix is not None:
|
|
filename = s3_prefix + "/" + filename
|
|
global_http_connection.download_file(
|
|
f"{VLLM_S3_BUCKET_URL}/{filename}",
|
|
asset_path,
|
|
timeout=envs.VLLM_IMAGE_FETCH_TIMEOUT,
|
|
)
|
|
|
|
return asset_path
|