Files
YG_FT/frontend/src/views/inference/InferenceCreateView.vue
wuyongtao 0271942ba5 feat: 模型推理异步加载与对话链路修复,同步基线
模型推理全异步化改造:
- 计算节点 InferenceSession 改为后台线程异步加载模型,load 立即返回,
  加载期间事件循环保持响应(/inference/status 与 /health 不阻塞)
- 后端模型加载改为异步派发 + 轮询对账器(reconcile_inference_loads),
  任务状态由 starting 自动推进到 ready/error,解决多节点启动超时
  (timeout of 120000ms exceeded)
- 推理删除/卸载改为任务感知 + 短超时,删除先删记录再 best-effort 卸载,
  不再被不可达节点阻塞;同节点新模型替换旧任务标记失效
- 流式对话透传 task_id/node_id 路由到真正加载模型的算力节点,
  useStreamChat 解析 SSE 错误帧以干净文案展示
- 对话历史按任务 id 本地持久化,退出重进可恢复;移除页脚提示文本
- 新增后端推理异步加载与计算节点异步状态机单元测试

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-04 16:59:34 +08:00

252 lines
8.1 KiB
Vue
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.
<script setup lang="ts">
import { ref, reactive, computed, onMounted, watch } from 'vue'
import { useRouter } from 'vue-router'
import { ElMessage, type FormInstance, type FormRules } from 'element-plus'
import PageCard from '@/components/PageCard.vue'
import { getModelList, getTrainedModels } from '@/api/modules/model'
import { getSystemInfo } from '@/api/modules/system'
import { getComputeNodes, type ComputeNode } from '@/api/modules/compute'
import { createCompare, loadCompare } from '@/api/modules/compare'
import type { ModelItem, TrainedModel, GpuInfo } from '@/types'
const router = useRouter()
const formRef = ref<FormInstance>()
const submitting = ref(false)
const startupStatus = ref('')
const dbModels = ref<ModelItem[]>([])
const trainedModels = ref<TrainedModel[]>([])
const gpus = ref<GpuInfo[]>([])
const computeNodes = ref<ComputeNode[]>([])
/** 可选模型(下拉用,区分本地/已训练两类) */
interface SelectableModel {
/** 下拉唯一值db-{id} / trained-{id} */
key: string
id: string | number
name: string
source: 'database' | 'trained'
model_path: string
compute_node_id?: string
compute_node_name?: string
merged?: boolean
merging?: boolean
disabled?: boolean
}
/** 本地模型选项 */
const dbOptions = computed<SelectableModel[]>(() =>
dbModels.value.map((m) => ({
key: `db-${m.id}`,
id: m.id,
name: m.name,
source: 'database',
model_path: m.path || '',
})),
)
/** 已训练模型选项(未合并的禁用) */
const trainedOptions = computed<SelectableModel[]>(() =>
trainedModels.value.map((m) => ({
key: `trained-${m.id}`,
id: m.id,
name: m.name,
source: 'trained',
model_path: m.merged_path || m.base_model_path || '',
compute_node_id: m.compute_node_id,
compute_node_name: m.compute_node_name,
merged: m.merged,
merging: m.merging,
disabled: m.merged === false,
})),
)
/** 仅显示在线算力节点上的空闲 GPU */
const onlineNodeIds = computed(() => new Set(
computeNodes.value
.filter((n) => n.enabled && n.scheduler_status === 'online')
.map((n) => n.id),
))
const idleGpus = computed(() =>
gpus.value.filter(
(g) => g.status === 'idle' && (!g.node_id || onlineNodeIds.value.has(g.node_id)),
),
)
const modelMap = computed<Record<string, SelectableModel>>(() => {
const map: Record<string, SelectableModel> = {}
for (const m of [...dbOptions.value, ...trainedOptions.value]) map[m.key] = m
return map
})
const form = reactive({
name: '',
description: '',
/** 选中的模型 key单选 */
model_key: '',
/** 使用的 GPU */
gpu_key: '',
})
const rules: FormRules = {
name: [{ required: true, message: '请输入推理名称', trigger: 'blur' }],
model_key: [{ required: true, message: '请选择模型', trigger: 'change' }],
}
/** 当前选中的模型对象 */
const selectedModel = computed(() => modelMap.value[form.model_key])
const selectedGpu = computed(() => idleGpus.value.find((g) => `${g.node_id || ''}:${g.id ?? 0}` === form.gpu_key))
watch(selectedModel, (model) => {
if (!model?.compute_node_id) return
const gpu = idleGpus.value.find((item) => item.node_id === model.compute_node_id)
if (gpu) form.gpu_key = `${gpu.node_id || ''}:${gpu.id ?? 0}`
})
async function handleSubmit() {
if (!formRef.value) return
await formRef.value.validate(async (valid) => {
if (!valid) return
const m = selectedModel.value
if (!m) {
ElMessage.warning('请选择模型')
return
}
submitting.value = true
startupStatus.value = '正在创建推理任务...'
try {
if (!m.model_path) {
ElMessage.warning('当前模型未配置算力节点可访问路径,请先在模型管理中维护模型路径')
return
}
// Step 1: 创建推理任务记录
const taskResult = await createCompare({
name: form.name || m.name,
description: form.description,
status: 'pending',
models: [
{
model_id: String(m.id),
model_name: m.name,
model_path: m.model_path,
source: m.source,
gpu_id: selectedGpu.value?.id ?? 0,
node_id: selectedGpu.value?.node_id || m.compute_node_id,
node_name: selectedGpu.value?.node_name || m.compute_node_name,
},
],
})
const taskId = taskResult?.id || 'unknown'
// Step 2: 统一通过推理任务加载接口异步派发模型加载,状态会落到列表记录中。
startupStatus.value = '正在启动模型服务,首次加载可能需要数分钟...'
const loadResult: any = await loadCompare(taskId)
if (loadResult?.status === 'failed' || loadResult?.error) {
ElMessage.warning(`模型加载失败:${loadResult?.error || '请检查算力节点日志'}`)
router.push('/model-inference')
return
}
// 加载为异步派发,回到列表页可看到“启动中 → 已就绪”的状态流转
ElMessage.success('模型加载中,就绪后即可对话')
router.push('/model-inference')
} catch (e: any) {
const reason = e?.message || e?.toString() || '未知错误'
ElMessage.warning(`推理服务启动失败:${reason}`)
} finally {
submitting.value = false
startupStatus.value = ''
}
})
}
function handleCancel() {
router.back()
}
async function loadData() {
try {
const [db, trained, sys, nodes] = await Promise.all([
getModelList(),
getTrainedModels(),
getSystemInfo(),
getComputeNodes(),
])
dbModels.value = db || []
trainedModels.value = trained?.models || []
gpus.value = sys?.gpu || []
computeNodes.value = nodes || []
// 默认选中第一个空闲 GPU
if (idleGpus.value.length > 0) {
const firstGpu = idleGpus.value[0]
form.gpu_key = `${firstGpu.node_id || ''}:${firstGpu.id ?? 0}`
}
} catch {
// ignore
}
}
onMounted(loadData)
</script>
<template>
<PageCard title="新建推理">
<el-form ref="formRef" :model="form" :rules="rules" label-width="100px">
<el-form-item label="推理名称" prop="name">
<el-input v-model="form.name" placeholder="请输入推理名称" maxlength="50" show-word-limit style="max-width: 400px" />
</el-form-item>
<el-form-item label="描述">
<el-input v-model="form.description" type="textarea" :rows="2" maxlength="200" show-word-limit style="max-width: 400px" />
</el-form-item>
<el-divider content-position="left">选择模型</el-divider>
<el-form-item label="选择模型" prop="model_key">
<el-select
v-model="form.model_key"
placeholder="请选择模型"
filterable
style="width: 400px"
>
<el-option-group label="本地模型">
<el-option
v-for="m in dbOptions"
:key="m.key"
:label="m.name"
:value="m.key"
/>
</el-option-group>
<el-option-group label="已训练模型">
<el-option
v-for="m in trainedOptions"
:key="m.key"
:label="m.name + (m.disabled ? '(未合并)' : '')"
:value="m.key"
:disabled="m.disabled"
/>
</el-option-group>
</el-select>
</el-form-item>
<el-form-item label="GPU">
<el-select v-model="form.gpu_key" style="width: 400px">
<el-option
v-for="g in idleGpus"
:key="`${g.node_id || ''}:${g.id ?? 0}`"
:label="`${g.node_name || g.node_code || '算力节点'} / ${g.name} (GPU${g.id ?? 0}) [空闲]`"
:value="`${g.node_id || ''}:${g.id ?? 0}`"
/>
</el-select>
</el-form-item>
<el-form-item v-if="startupStatus" label="启动状态">
<el-alert :title="startupStatus" type="info" :closable="false" show-icon />
</el-form-item>
<el-form-item>
<el-button type="primary" :loading="submitting" @click="handleSubmit">开始推理</el-button>
<el-button @click="handleCancel">取消</el-button>
</el-form-item>
</el-form>
</PageCard>
</template>