后端: - 抽取 fetch_eval_result_content 复用函数,model_eval_detail 直接应用评测任务结果 - health 接口移除数据库依赖,返回静态指标 - 数据集: count_dataset_records JSON 感知计数; 文件统计改为从 dataset_files 聚合重算; 在线编辑记录 size/record_count/version_no; 上传同步批处理 - 算力节点: 调度支持 requested GPU 子集校验与容量计算; 新增 delete_compute_node(含活动任务保护)及 DELETE 接口; 连接池 connect_timeout - 评测任务落库 basic_metrics/score/completed_time, failed/stopped 记录 error 评测引擎: - _load_dataset 支持 JSON/JSONL 文件 - 新增 exact match 与文本相似度指标, 余弦相似度去掉 2 样本限制 前端: - 算力节点列表「维护」改为「删除」(带确认弹窗), compute.ts 新增 deleteComputeNode - 数据集上传超时调整为 120s; FineTuneTask 增加 compute_node_id; GpuInfo 状态增加 reserved
126 lines
3.4 KiB
TypeScript
126 lines
3.4 KiB
TypeScript
import { del, get, post, put } from '../request'
|
|
|
|
export interface ComputeNode {
|
|
id: string
|
|
code: string
|
|
name: string
|
|
api_base_url: string
|
|
file_gateway_url: string
|
|
enabled: boolean
|
|
scheduler_status: string
|
|
scheduler_weight: number
|
|
tags: string[]
|
|
gpu_count: number
|
|
current_running_jobs: number
|
|
max_parallel_jobs: number
|
|
data_root: string
|
|
model_root: string
|
|
log_root: string
|
|
api_version?: string
|
|
capabilities?: string[]
|
|
description?: string
|
|
last_health_check_at?: string
|
|
health_detail?: Record<string, unknown>
|
|
}
|
|
|
|
export type ComputeNodePayload = Partial<ComputeNode> & {
|
|
code?: string
|
|
api_base_url?: string
|
|
}
|
|
|
|
export interface ComputeGpu {
|
|
id: number
|
|
node_id: string
|
|
node_code: string
|
|
node_name: string
|
|
name: string
|
|
uuid: string
|
|
status: string
|
|
gpu_percent: number
|
|
memory_used_gb: number
|
|
memory_total_gb: number
|
|
memory_percent: number
|
|
temperature: number
|
|
power_w: number
|
|
power_limit_w: number
|
|
processes?: Array<{
|
|
pid: number
|
|
name: string
|
|
memory_used_gb: number
|
|
task_name?: string
|
|
user?: string
|
|
}>
|
|
}
|
|
|
|
export interface ComputeQueueItem {
|
|
id: string
|
|
name: string
|
|
status: string
|
|
progress: number
|
|
compute_node_id?: string
|
|
gpus: number[]
|
|
create_time?: string
|
|
}
|
|
|
|
export interface ResourceReplica {
|
|
id: string
|
|
node_id: string
|
|
resource_type: string
|
|
resource_id: string
|
|
local_path: string
|
|
status: string
|
|
sync_status: string
|
|
checksum_sha256?: string
|
|
byte_size?: number
|
|
last_checked_at?: string
|
|
last_error?: string
|
|
create_time: string
|
|
}
|
|
|
|
export interface ResourceSyncJob {
|
|
id: string
|
|
target_node_id: string
|
|
resources?: unknown
|
|
status: string
|
|
progress: number
|
|
create_time?: string
|
|
completed_at?: string
|
|
}
|
|
|
|
export const getComputeNodes = () => get<ComputeNode[]>('/compute/nodes')
|
|
|
|
export const createComputeNode = (data: ComputeNodePayload) =>
|
|
post<ComputeNode>('/compute/nodes', data)
|
|
|
|
export const updateComputeNode = (id: string, data: Partial<ComputeNode>) =>
|
|
put<ComputeNode>(`/compute/nodes/${id}`, data)
|
|
|
|
export const deleteComputeNode = (id: string) =>
|
|
del<{ deleted: string }>(`/compute/nodes/${id}`)
|
|
|
|
export const testComputeNode = (id: string) =>
|
|
post<{ node_id: string; success: boolean; latency_ms: number; gpu_count: number; error?: string }>(`/compute/nodes/${id}/test-connection`)
|
|
|
|
export const enableComputeNode = (id: string) => post<ComputeNode>(`/compute/nodes/${id}/enable`)
|
|
|
|
export const disableComputeNode = (id: string) => post<ComputeNode>(`/compute/nodes/${id}/disable`)
|
|
|
|
export const drainComputeNode = (id: string) => post<ComputeNode>(`/compute/nodes/${id}/drain`)
|
|
|
|
export const getComputeGpus = () => get<ComputeGpu[]>('/compute/gpus')
|
|
|
|
export const getComputeQueue = () => get<ComputeQueueItem[]>('/compute/queue')
|
|
|
|
export const getNodeReplicas = (id: string) => get<ResourceReplica[]>(`/compute/nodes/${id}/replicas`)
|
|
|
|
export const checkNodeReplicaDrift = (id: string) =>
|
|
get<{ node_id: string; items: ResourceReplica[]; drifted: number }>(`/compute/nodes/${id}/replicas/drift`)
|
|
|
|
export const repairNodeReplicas = (id: string, replicaIds?: string[]) =>
|
|
post<{ sync: ResourceSyncJob; replicas: ResourceReplica[]; failed: Array<{ replica_id: string; error: string }>; async?: boolean }>(
|
|
`/compute/nodes/${id}/replicas/repair`,
|
|
replicaIds?.length ? { replica_ids: replicaIds } : {},
|
|
)
|
|
|
|
export const getComputeSyncJob = (id: string) => get<ResourceSyncJob>(`/compute/sync-jobs/${id}`)
|