feat(multimodal): 补齐阶段F运行管理与收尾验收

This commit is contained in:
2026-09-05 01:06:29 +08:00
parent 6bdba2c7f9
commit 64f63ff1bd
29 changed files with 838 additions and 84 deletions
@@ -2,11 +2,11 @@
import { onMounted, onUnmounted, ref } from 'vue'
import { apiClient } from '@/services/apiClient'
interface Config {device: 'cpu'|'cuda'; cpu_threads: number; memory_limit_mb: number; gpu_memory_limit_mb: number; timeout_seconds: number; embedding_model: string; version: number}
interface Model {key: string; name: string; capability: string; revision: string; license: string; status: string; downloaded_bytes: number; total_bytes: number|null; error_code?: string}
interface Model {key: string; name: string; capability: string; revision: string; license: string; status: string; disk_bytes: number|null; downloaded_bytes: number; total_bytes: number|null; error_code?: string}
const items = ref<Model[]>([])
const config = ref<Config | null>(null)
const installed = ref(false)
const lastInference = ref<{actual_device:string;requested_device:string;inference_seconds:number}|null>(null)
const lastInference = ref<{actual_device:string;requested_device:string;inference_seconds?:number;elapsed_seconds?:number;status?:string;error_code?:string}|null>(null)
const error = ref('')
const dirty = ref(false)
const busy = ref(false)
@@ -43,7 +43,7 @@ onUnmounted(() => { stopped = true; clearTimeout(timer) })
<section class="local-models">
<h3>本地模型</h3><p class="subtle">默认 CPU下载需要联网推理只读取本地权重文件校验通过不代表当前设备已完成推理验证</p>
<p v-if="error" class="error-banner" role="alert">{{ error }}</p>
<p v-if="lastInference" class="subtle">最近实际运行{{ lastInference.actual_device }} · 请求设备 {{ lastInference.requested_device }} · 推理 {{ lastInference.inference_seconds.toFixed(2) }} </p>
<p v-if="lastInference" class="subtle">最近实际运行{{ lastInference.actual_device || '未开始推理' }} · 请求设备 {{ lastInference.requested_device }} · 推理 {{ (lastInference.inference_seconds ?? lastInference.elapsed_seconds ?? 0).toFixed(2) }} · {{ lastInference.status }} {{ lastInference.error_code || '' }}</p>
<p v-if="!installed" class="subtle">尚未安装模型运行环境在项目根目录执行 <code>./backend/scripts/install-model-runtime.ps1</code>CUDA 选装追加 <code>-Device cuda</code></p>
<form v-if="config" @submit.prevent="save" @input="dirty = true" @change="dirty = true">
<div class="runtime-grid"><label>请求设备<select v-model="config.device" class="select"><option value="cpu">CPU(默认)</option><option value="cuda">CUDA不可用则 CPU</option></select></label>
@@ -54,12 +54,12 @@ onUnmounted(() => { stopped = true; clearTimeout(timer) })
<p class="subtle">修改 Embedding 后需要重建索引任务按预算串行运行模型在任务结束后释放</p><button class="button-primary" :disabled="busy || !dirty">保存运行设置</button>
</form>
<div class="model-grid"><article v-for="model in items" :key="model.key" class="item-card"><h4>{{ model.name }}</h4><p>{{ model.license }} · {{ labels[model.status] || model.status }}</p><small :title="model.revision">版本 {{ model.revision.slice(0,12) }}</small>
<p>{{ size(model.downloaded_bytes) }} / {{ size(model.total_bytes) }}</p><progress v-if="model.status === 'downloading' && model.total_bytes" :value="model.downloaded_bytes" :max="model.total_bytes" />
<p>实际磁盘占用 {{ size(model.disk_bytes) }}</p><p>{{ size(model.downloaded_bytes) }} / {{ size(model.total_bytes) }}</p><progress v-if="model.status === 'downloading' && model.total_bytes" :value="model.downloaded_bytes" :max="model.total_bytes" />
<p v-if="model.error_code" class="error-text">{{ model.error_code }}</p><div class="inline-actions">
<button v-if="model.status !== 'installed' && model.status !== 'downloading'" class="button-secondary" :disabled="busy" @click="act(() => apiClient.post(`/api/local-models/${model.key}/download`))">{{ model.status === 'not_installed' ? '下载模型' : '重试 / 续传' }}</button>
<button v-if="model.status === 'downloading'" class="button-secondary" :disabled="busy" @click="act(() => apiClient.post(`/api/local-models/${model.key}/cancel`))">暂停</button>
<button v-if="model.status !== 'not_installed'" class="button-danger" :disabled="busy" @click="act(() => apiClient.delete(`/api/local-models/${model.key}`))">删除权重</button></div>
</article></div><button class="button-secondary" @click="diagnostics">导出本次运行诊断</button><p class="subtle">诊断仅包含模型设备耗时和资源信息不包含正文音频和密钥</p>
</article></div><button class="button-secondary" @click="diagnostics">导出最近运行诊断</button><p class="subtle">诊断仅包含模型设备耗时和资源信息不包含正文音频和密钥</p>
</section>
</template>
<style scoped>.local-models{display:grid;gap:16px}.runtime-grid,.model-grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(220px,1fr));gap:12px}label{display:grid;gap:6px}.item-card{padding:16px}progress{width:100%}</style>