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

109 lines
3.9 KiB
Python
Raw Normal View History

"""GPU 算力分配管理路由。"""
from __future__ import annotations
import json
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, user_tenant_ids
from app.db.platform_store import get_platform_store
router = APIRouter(prefix="/compute", tags=["gpu-assignment"])
@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 = current_user.get("id")
try:
result = get_platform_store().assign_gpus(assignments, assigned_by=actor)
except ValueError as exc:
raise fail(409, str(exc))
get_platform_store().record_audit(
action="gpu.assign",
actor_id=actor,
target_type="gpu",
detail=f"count={len(assignments)}",
)
return ok(result)
@router.post("/gpu-assignments/request")
def request_gpu_assignment(
payload: dict[str, Any] = Body(...),
current_user: dict = Depends(get_current_user),
) -> dict[str, Any]:
assignments = payload.get("assignments") or []
if not assignments:
raise fail(400, "assignments 不能为空")
if is_admin(current_user):
try:
return ok(get_platform_store().assign_gpus(assignments, assigned_by=current_user.get("id")))
except ValueError as exc:
raise fail(409, str(exc))
user_id = str(current_user.get("id") or "")
normalized = []
for item in assignments:
if not isinstance(item, dict) or not item.get("node_id") or item.get("gpu_index") is None:
raise fail(400, "每项必须包含 node_id 和 gpu_index")
normalized.append({**item, "user_id": user_id})
instance = get_platform_store().create_approval_instance({
"resource_type": "gpu",
"resource_id": f"batch:{user_id}",
"applicant_id": user_id,
"action": "gpu.assign",
"tenant_id": current_user.get("tenant_id") or "default",
"reason": json.dumps({"assignments": normalized}, ensure_ascii=False),
})
get_platform_store().record_audit(
action="gpu.assign.request", actor_id=user_id, target_type="gpu",
target_id=instance["id"], tenant_id=current_user.get("tenant_id") or "default",
detail=f"count={len(normalized)}",
)
return ok({"approval_required": True, "approval_id": instance["id"], "approval": instance})
@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 = current_user.get("id")
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"]))