Files
YG_FT/backend/app/modules/gpu/router.py

78 lines
2.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""GPU 算力分配管理路由。"""
from __future__ import annotations
from typing import Any
from fastapi import APIRouter, Body, Depends, Request
from app.api.v1.endpoints.platform import ok, fail
from app.core.auth import get_current_user, is_admin
from app.db.platform_store import get_platform_store
router = APIRouter(prefix="/compute", tags=["gpu-assignment"])
def _actor_id(request: Request) -> str | None:
auth = request.headers.get("Authorization", "")
token = auth.replace("Bearer ", "").strip()
if token.startswith("platform-token-"):
return token[len("platform-token-"):]
return None
@router.get("/gpu-assignments")
def list_assignments(current_user: dict = Depends(get_current_user)) -> dict[str, Any]:
"""查看全部分配关系(仅 admin"""
if not is_admin(current_user):
raise fail(403, "admin permission required")
return ok(get_platform_store().gpu_assignments())
@router.post("/gpu-assignments")
def assign_gpus(
payload: dict[str, Any] = Body(...),
request: Request = None,
current_user: dict = Depends(get_current_user),
) -> dict[str, Any]:
"""批量分配 GPU仅 admin。body: { assignments: [{ node_id, gpu_index, user_id }] }"""
if not is_admin(current_user):
raise fail(403, "admin permission required")
assignments = payload.get("assignments") or []
if not assignments:
raise fail(400, "assignments 不能为空")
actor = _actor_id(request) if request else None
result = get_platform_store().assign_gpus(assignments, assigned_by=actor)
get_platform_store().record_audit(
action="gpu.assign",
actor_id=actor,
target_type="gpu",
detail=f"count={len(assignments)}",
)
return ok(result)
@router.delete("/gpu-assignments/{assignment_id}")
def unassign_gpu(
assignment_id: str,
request: Request = None,
current_user: dict = Depends(get_current_user),
) -> dict[str, Any]:
"""撤销 GPU 分配(仅 admin"""
if not is_admin(current_user):
raise fail(403, "admin permission required")
get_platform_store().unassign_gpu(assignment_id)
actor = _actor_id(request) if request else None
get_platform_store().record_audit(
action="gpu.unassign",
actor_id=actor,
target_type="gpu",
target_id=assignment_id,
)
return ok({"deleted": assignment_id})
@router.get("/my-gpus")
def my_gpus(current_user: dict = Depends(get_current_user)) -> dict[str, Any]:
"""查看当前用户可用的 GPU 列表。"""
return ok(get_platform_store().gpu_assignments_for_user(current_user["id"]))