94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
110 lines
3.5 KiB
Python
110 lines
3.5 KiB
Python
import asyncio
|
|
import os
|
|
from typing import Optional
|
|
|
|
from sglang.multimodal_gen.runtime.utils.logging_utils import init_logger
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
|
|
class CloudStorage:
|
|
def __init__(self):
|
|
self.enabled = os.getenv("SGLANG_CLOUD_STORAGE_TYPE", "").lower() == "s3"
|
|
if not self.enabled:
|
|
return
|
|
|
|
try:
|
|
import boto3
|
|
except ImportError:
|
|
logger.error(
|
|
"boto3 is not installed. Please install it with `pip install boto3` to use cloud storage."
|
|
)
|
|
self.enabled = False
|
|
return
|
|
|
|
self.bucket_name = os.getenv("SGLANG_S3_BUCKET_NAME")
|
|
if not self.bucket_name:
|
|
self.enabled = False
|
|
return
|
|
|
|
endpoint_url = os.getenv("SGLANG_S3_ENDPOINT_URL") or None
|
|
region_name = os.getenv("SGLANG_S3_REGION_NAME") or None
|
|
|
|
self.client = boto3.client(
|
|
"s3",
|
|
aws_access_key_id=os.getenv("SGLANG_S3_ACCESS_KEY_ID"),
|
|
aws_secret_access_key=os.getenv("SGLANG_S3_SECRET_ACCESS_KEY"),
|
|
endpoint_url=endpoint_url,
|
|
region_name=region_name,
|
|
)
|
|
self.endpoint_url = endpoint_url
|
|
self.region_name = region_name
|
|
|
|
def is_enabled(self) -> bool:
|
|
return self.enabled
|
|
|
|
async def upload_file(self, local_path: str, destination_key: str) -> Optional[str]:
|
|
if not self.is_enabled():
|
|
return None
|
|
|
|
def _sync_upload():
|
|
"""Synchronous part of the upload to run in a thread."""
|
|
ext = os.path.splitext(local_path)[1].lower()
|
|
content_type = {
|
|
".png": "image/png",
|
|
".jpg": "image/jpeg",
|
|
".jpeg": "image/jpeg",
|
|
".webp": "image/webp",
|
|
".mp4": "video/mp4",
|
|
".glb": "model/gltf-binary",
|
|
".obj": "text/plain",
|
|
}.get(ext, "application/octet-stream")
|
|
|
|
# Use the client created once in __init__
|
|
self.client.upload_file(
|
|
local_path,
|
|
self.bucket_name,
|
|
destination_key,
|
|
ExtraArgs={"ContentType": content_type},
|
|
)
|
|
|
|
try:
|
|
# Offload the blocking I/O call to a thread executor
|
|
await asyncio.get_running_loop().run_in_executor(None, _sync_upload)
|
|
except Exception as e:
|
|
# If upload fails, log the error and return None for fallback
|
|
logger.error(f"Upload failed for {destination_key}: {e}")
|
|
return None
|
|
|
|
# Simplified URL generation with a default region
|
|
if self.endpoint_url:
|
|
url = (
|
|
f"{self.endpoint_url.rstrip('/')}/{self.bucket_name}/{destination_key}"
|
|
)
|
|
else:
|
|
region = self.region_name or "us-east-1"
|
|
url = f"https://{self.bucket_name}.s3.{region}.amazonaws.com/{destination_key}"
|
|
|
|
logger.info(f"Uploaded {local_path} to {url}")
|
|
return url
|
|
|
|
async def upload_and_cleanup(self, file_path: str) -> Optional[str]:
|
|
"""Helper to upload a file and delete the local copy if successful."""
|
|
if not self.is_enabled():
|
|
return None
|
|
|
|
key = os.path.basename(file_path)
|
|
url = await self.upload_file(file_path, key)
|
|
|
|
if url:
|
|
try:
|
|
# pass if removal fails
|
|
os.remove(file_path)
|
|
except OSError as e:
|
|
logger.warning(f"Failed to remove temporary file {file_path}: {e}")
|
|
return url
|
|
|
|
|
|
# Global instance
|
|
cloud_storage = CloudStorage()
|