feat(gpu-service): align instance-type/flavor contract with status.detail API
- spec keeps definition fields only; observed hardware read from status.detail - sliceable derived from slicedDetail (logical count / physical profiles) - flat snapshot format isolated in instance-description for back-compat - drop flavor.spec.sliceable; onceMaxRequest realigned (no ram/localStorage) - lock compute ratio to memory ratio when coresPercentageOvercommit is false - sliced mode submits whole cores / Gi; displayName-first type labels
This commit is contained in:
jialin
@@ -122,6 +122,7 @@ export default {
|
||||
'gpuservice.instance.mode.whole': 'Full GPU',
|
||||
'gpuservice.instance.mode.sliced': 'By Ratio',
|
||||
'gpuservice.instance.slice.memoryPercentage': 'VRAM Percentage (%)',
|
||||
'gpuservice.instance.slice.percentage': 'Percentage (%)',
|
||||
'gpuservice.instance.slice.coresPercentage': 'Compute Percentage (%)',
|
||||
'gpuservice.instance.slice.cores.min':
|
||||
'The compute ratio must be no less than the VRAM ratio ({count}%)',
|
||||
|
||||
@@ -121,6 +121,7 @@ export default {
|
||||
'gpuservice.instance.mode.whole': 'GPU 全体',
|
||||
'gpuservice.instance.mode.sliced': '比率で',
|
||||
'gpuservice.instance.slice.memoryPercentage': 'VRAM の割合（%）',
|
||||
'gpuservice.instance.slice.percentage': '割合（%）',
|
||||
'gpuservice.instance.slice.coresPercentage': '演算能力の割合（%）',
|
||||
'gpuservice.instance.slice.cores.min':
|
||||
'演算能力の割合は VRAM の割合（{count}%）以上である必要があります',
|
||||
|
||||
@@ -120,6 +120,7 @@ export default {
|
||||
'gpuservice.instance.mode.whole': 'Весь GPU',
|
||||
'gpuservice.instance.mode.sliced': 'По доле',
|
||||
'gpuservice.instance.slice.memoryPercentage': 'Доля VRAM (%)',
|
||||
'gpuservice.instance.slice.percentage': 'Доля (%)',
|
||||
'gpuservice.instance.slice.coresPercentage': 'Доля вычислений (%)',
|
||||
'gpuservice.instance.slice.cores.min':
|
||||
'Доля вычислений должна быть не меньше доли VRAM ({count}%)',
|
||||
|
||||
@@ -116,6 +116,7 @@ export default {
|
||||
'gpuservice.instance.mode.whole': 'Tam GPU',
|
||||
'gpuservice.instance.mode.sliced': 'Orana Göre',
|
||||
'gpuservice.instance.slice.memoryPercentage': 'VRAM Yüzdesi (%)',
|
||||
'gpuservice.instance.slice.percentage': 'Yüzde (%)',
|
||||
'gpuservice.instance.slice.coresPercentage': 'İşlem Gücü Yüzdesi (%)',
|
||||
'gpuservice.instance.slice.cores.min':
|
||||
'İşlem gücü oranı VRAM oranından ({count}%) küçük olamaz',
|
||||
|
||||
@@ -111,6 +111,7 @@ export default {
|
||||
'gpuservice.instance.mode.whole': '整卡',
|
||||
'gpuservice.instance.mode.sliced': '按比例',
|
||||
'gpuservice.instance.slice.memoryPercentage': '显存占比（%）',
|
||||
'gpuservice.instance.slice.percentage': '占比（%）',
|
||||
'gpuservice.instance.slice.coresPercentage': '算力占比（%）',
|
||||
'gpuservice.instance.slice.cores.min': '算力占比需不小于显存占比 {count}%',
|
||||
'gpuservice.instance.slice.fullCores': '100% 算力',
|
||||
|
||||
@@ -53,7 +53,7 @@ export async function deleteGPUInstanceType(params: {
|
||||
});
|
||||
}
|
||||
|
||||
// PUT /gpu-instance-types/{name}/enactive?cluster_id — activate an instance type.
|
||||
// PUT /gpu-instance-types/{name}/activate?cluster_id — activate an instance type.
|
||||
export async function activateGPUInstanceType(params: {
|
||||
name: string;
|
||||
cluster_id: number;
|
||||
@@ -64,7 +64,7 @@ export async function activateGPUInstanceType(params: {
|
||||
});
|
||||
}
|
||||
|
||||
// PUT /gpu-instance-types/{name}/deactive?cluster_id — deactivate an instance type.
|
||||
// PUT /gpu-instance-types/{name}/deactivate?cluster_id — deactivate an instance type.
|
||||
export async function deactivateGPUInstanceType(params: {
|
||||
name: string;
|
||||
cluster_id: number;
|
||||
|
||||
@@ -5,9 +5,10 @@ import { formatMemoryDisplay } from '../../instances/config';
|
||||
import { manufactureColorMap } from '../../templates/config';
|
||||
import { formatManufacturer } from '../../utils';
|
||||
|
||||
// The subset of a flavor / instance-type spec the flavor display reads. Both
|
||||
// FlavorItem.spec and InstanceTypeSpec structurally satisfy it, so the create
|
||||
// drawer's dropdown and the management list share the same renderers.
|
||||
// The subset of a flavor / instance-type display shape the flavor renderers
|
||||
// read. Flavor specs satisfy it directly (minus sliceable, which the API
|
||||
// removed from flavors); the management list builds it from spec.acceleratable
|
||||
// + status.detail, deriving sliceable from slicedDetail.
|
||||
interface FlavorSpecLike {
|
||||
manufacturer?: string | null;
|
||||
product?: string | null;
|
||||
@@ -58,17 +59,6 @@ export const FlavorMeta: React.FC<{ spec?: FlavorSpecLike }> = ({
|
||||
if (memory) {
|
||||
pieces.push(<span key="memory">{memory}</span>);
|
||||
}
|
||||
if (spec.acceleratable && spec.sliceable) {
|
||||
pieces.push(
|
||||
<ThemeTag
|
||||
key="sliceable"
|
||||
color="geekblue"
|
||||
style={{ fontWeight: 400, marginInlineEnd: 0 }}
|
||||
>
|
||||
{intl.formatMessage({ id: 'gpuservice.instance.sliceable' })}
|
||||
</ThemeTag>
|
||||
);
|
||||
}
|
||||
if (!pieces.length) return null;
|
||||
|
||||
return (
|
||||
|
||||
@@ -94,8 +94,10 @@ const FlavorList: React.FC<FlavorListProps> = ({
|
||||
</ThemeTag>
|
||||
)}
|
||||
</Flex>
|
||||
{/* Memory / sliceable only apply to accelerator (GPU) flavors;
|
||||
a non-acceleratable (generic) flavor has neither. */}
|
||||
{/* Memory only applies to accelerator (GPU) flavors; a
|
||||
non-acceleratable (generic) flavor has none. (Sliceable is no
|
||||
longer a flavor field — it is observed per instance type on
|
||||
status.detail.slicedDetail.) */}
|
||||
{spec.acceleratable && (
|
||||
<Flex wrap gap={16}>
|
||||
<MetaItem
|
||||
@@ -105,17 +107,6 @@ const FlavorList: React.FC<FlavorListProps> = ({
|
||||
})}
|
||||
value={formatMemoryDisplay(spec.memory ?? undefined) ?? '-'}
|
||||
/>
|
||||
<MetaItem
|
||||
icon="icon-sliced"
|
||||
label={intl.formatMessage({
|
||||
id: 'gpuservice.instance.sliceable'
|
||||
})}
|
||||
value={
|
||||
spec.sliceable
|
||||
? intl.formatMessage({ id: 'common.table.yes' })
|
||||
: intl.formatMessage({ id: 'common.table.no' })
|
||||
}
|
||||
/>
|
||||
</Flex>
|
||||
)}
|
||||
</Flex>
|
||||
|
||||
@@ -9,7 +9,7 @@ import {
|
||||
import { useIntl } from '@umijs/max';
|
||||
import { Button } from 'antd';
|
||||
import _ from 'lodash';
|
||||
import { formatMemoryDisplay } from '../../instances/config';
|
||||
import { formatMemoryDisplay, isSliceableDetail } from '../../instances/config';
|
||||
import { manufactureColorMap } from '../../templates/config';
|
||||
import { ceilMilliToCore, parseQuantityToGi } from '../../utils';
|
||||
import {
|
||||
@@ -31,12 +31,16 @@ const InstanceTypeCard: React.FC<InstanceTypeCardProps> = ({
|
||||
}) => {
|
||||
const intl = useIntl();
|
||||
const spec = data.spec || {};
|
||||
// Observed hardware (manufacturer / memory / sliced capability, …) comes
|
||||
// from status.detail and may be absent until the operator backfills status.
|
||||
const detail = data.status?.detail || {};
|
||||
const unit = spec.unitResources || {};
|
||||
const phase = data.status?.phase || '';
|
||||
const manufacturer = spec.manufacturer || '';
|
||||
const manufacturer = detail.manufacturer || '';
|
||||
const manufacturerColor = manufactureColorMap[manufacturer] ?? 'purple';
|
||||
const sliceable = isSliceableDetail(detail.slicedDetail);
|
||||
|
||||
const memoryText = formatMemoryDisplay(spec.memory ?? undefined);
|
||||
const memoryText = formatMemoryDisplay(detail.memory ?? undefined);
|
||||
|
||||
// Base resources, formatted into a single "·"-separated line. Falsy parts
|
||||
// (e.g. a CPU-only type without VRAM) drop out rather than showing "-".
|
||||
@@ -71,7 +75,7 @@ const InstanceTypeCard: React.FC<InstanceTypeCardProps> = ({
|
||||
<div className={styles.header}>
|
||||
<span className={styles.product}>
|
||||
<AutoTooltip ghost minWidth={20}>
|
||||
{spec.product || data.name || '-'}
|
||||
{detail.product || data.name || '-'}
|
||||
</AutoTooltip>
|
||||
</span>
|
||||
<span className={styles.headerRight}>
|
||||
@@ -115,13 +119,13 @@ const InstanceTypeCard: React.FC<InstanceTypeCardProps> = ({
|
||||
}}
|
||||
/>
|
||||
) : null}
|
||||
{spec.clockSpeed ? <span>{spec.clockSpeed}</span> : null}
|
||||
{detail.clockSpeed ? <span>{detail.clockSpeed}</span> : null}
|
||||
<span
|
||||
className={`${styles.tag} ${
|
||||
spec.sliceable ? styles.tagSliceable : styles.tagPlain
|
||||
sliceable ? styles.tagSliceable : styles.tagPlain
|
||||
}`}
|
||||
>
|
||||
{spec.sliceable
|
||||
{sliceable
|
||||
? intl.formatMessage({ id: 'gpuservice.instance.sliceable' })
|
||||
: intl.formatMessage({
|
||||
id: 'gpuservice.instanceType.notSliceable'
|
||||
|
||||
@@ -1,17 +1,17 @@
|
||||
import {
|
||||
InstanceTypeDetail,
|
||||
InstanceTypeResource
|
||||
} from '../../instances/config/types';
|
||||
|
||||
export interface UnitResources {
|
||||
cpu?: string | null;
|
||||
ram?: string | null;
|
||||
}
|
||||
|
||||
// spec carries user-defined fields only; observed hardware (manufacturer,
|
||||
// memory, sliced capability, …) lives on status.detail.
|
||||
export interface InstanceTypeSpec {
|
||||
displayName?: string | null;
|
||||
manufacturer?: string | null;
|
||||
product?: string | null;
|
||||
family?: string | null;
|
||||
memory?: string | null;
|
||||
cores?: string | null;
|
||||
clockSpeed?: string | null;
|
||||
sliceable?: boolean;
|
||||
os?: string | null;
|
||||
arch?: string | null;
|
||||
acceleratable?: boolean;
|
||||
@@ -22,8 +22,15 @@ export interface InstanceTypeSpec {
|
||||
}
|
||||
|
||||
export interface InstanceTypeStatus {
|
||||
// Observed hardware descriptor; absent until the operator backfills status.
|
||||
detail?: InstanceTypeDetail | null;
|
||||
phase?: string | null;
|
||||
phaseMessage?: string | null;
|
||||
// Per-mode resource accounting ({onceMaxRequest, remaining, capacity}).
|
||||
accelerator?: InstanceTypeResource | null;
|
||||
acceleratorShared?: InstanceTypeResource | null;
|
||||
acceleratorSliced?: InstanceTypeResource | null;
|
||||
cpu?: InstanceTypeResource | null;
|
||||
}
|
||||
|
||||
// Row shape for the management list (GET /gpu-instance-types).
|
||||
@@ -44,7 +51,6 @@ export interface FlavorItem {
|
||||
family?: string | null;
|
||||
memory?: string | null;
|
||||
cores?: string | null;
|
||||
sliceable?: boolean;
|
||||
acceleratable?: boolean;
|
||||
acceleratorGroup?: string | null;
|
||||
generalGroup?: string | null;
|
||||
|
||||
@@ -10,6 +10,7 @@ import { Space, Tooltip } from 'antd';
|
||||
import type { ColumnsType } from 'antd/lib/table';
|
||||
import _ from 'lodash';
|
||||
import { useMemo } from 'react';
|
||||
import { isSliceableDetail } from '../../instances/config';
|
||||
import { ceilMilliToCore, parseQuantityToGi } from '../../utils';
|
||||
import { FlavorOption } from '../components/flavor-display';
|
||||
import {
|
||||
@@ -95,17 +96,28 @@ const useInstanceTypeColumns = ({
|
||||
{
|
||||
// Flavor cell mirrors the create drawer's dropdown: product name on
|
||||
// top, manufacturer · memory · sliceable on the meta line below.
|
||||
// Observed hardware comes from status.detail (absent until the
|
||||
// operator backfills status); sliceable is derived from slicedDetail.
|
||||
title: intl.formatMessage({ id: 'gpuservice.instanceType.flavor' }),
|
||||
dataIndex: ['spec', 'product'],
|
||||
dataIndex: ['status', 'detail', 'product'],
|
||||
key: 'product',
|
||||
ellipsis: { showTitle: false },
|
||||
render: (_text: string, record: ListItem) => (
|
||||
<FlavorOption
|
||||
spec={record.spec}
|
||||
fallbackName={record.name}
|
||||
maxWidth={200}
|
||||
/>
|
||||
)
|
||||
render: (_text: string, record: ListItem) => {
|
||||
const detail = record.status?.detail;
|
||||
return (
|
||||
<FlavorOption
|
||||
spec={{
|
||||
acceleratable: record.spec?.acceleratable,
|
||||
manufacturer: detail?.manufacturer,
|
||||
product: detail?.product,
|
||||
memory: detail?.memory,
|
||||
sliceable: isSliceableDetail(detail?.slicedDetail)
|
||||
}}
|
||||
fallbackName={record.name}
|
||||
maxWidth={200}
|
||||
/>
|
||||
);
|
||||
}
|
||||
},
|
||||
{
|
||||
title: (
|
||||
|
||||
@@ -193,10 +193,13 @@ const AddModal: React.FC<AddModalProps> = ({
|
||||
: undefined;
|
||||
};
|
||||
|
||||
// GPU types carry their accelerator vendor; non-acceleratable (CPU) types
|
||||
// all map to the single 'cpu' bucket used to match templates.
|
||||
// GPU types carry their accelerator vendor on status.detail (observed — may
|
||||
// be absent until the operator backfills status); non-acceleratable (CPU)
|
||||
// types all map to the single 'cpu' bucket used to match templates.
|
||||
const manufacturerOf = (instanceType: InstanceTypeItem) =>
|
||||
instanceType.spec.acceleratable ? instanceType.spec?.manufacturer : 'cpu';
|
||||
instanceType.spec.acceleratable
|
||||
? (instanceType.status?.detail?.manufacturer ?? undefined)
|
||||
: 'cpu';
|
||||
|
||||
// apply the selection of instance type and template
|
||||
const applySelection = (
|
||||
|
||||
@@ -7,7 +7,11 @@ import styled from 'styled-components';
|
||||
import { manufactureColorMap } from '../../templates/config';
|
||||
import { formatManufacturer } from '../../utils';
|
||||
import { formatMemoryDisplay } from '../config';
|
||||
import { InstanceTypeItem as InstanceTypeItemModel } from '../config/types';
|
||||
import {
|
||||
InstanceTypeItem as InstanceTypeItemModel,
|
||||
InstanceTypeSnapshotSpec
|
||||
} from '../config/types';
|
||||
import { buildInstanceTypeSnapshotSpec } from '../utils/instance-description';
|
||||
|
||||
const Title = styled.div`
|
||||
display: flex;
|
||||
@@ -58,7 +62,10 @@ interface InstanceTypeItemProps {
|
||||
}
|
||||
|
||||
interface MetadataSectionProps {
|
||||
spec: InstanceTypeItemModel['spec'];
|
||||
// The flat snapshot / display model — built from a live item with
|
||||
// buildInstanceTypeSnapshotSpec, or parsed back from a persisted
|
||||
// `description` snapshot (readonly edit card).
|
||||
spec: InstanceTypeSnapshotSpec;
|
||||
// status.onceMaxRequest.acceleratorSliced (max sliceable percentage). Shown
|
||||
// next to Max for sliceable types.
|
||||
slicedMaxPercentage?: number;
|
||||
@@ -104,8 +111,14 @@ const CPUManufacturerTag: React.FC<{ manufacturer?: string }> = ({
|
||||
);
|
||||
};
|
||||
|
||||
function getInstanceDerived(item: InstanceTypeItemModel) {
|
||||
const spec = item.spec || {};
|
||||
// Derives the display fields from the flat snapshot spec (the UI document
|
||||
// format — built from a live item with buildInstanceTypeSnapshotSpec, or
|
||||
// parsed back from a persisted `description` snapshot). Observed hardware
|
||||
// (manufacturer / product / memory / cpu) originates from status.detail.
|
||||
function getInstanceDerived(
|
||||
spec: InstanceTypeSnapshotSpec = {},
|
||||
fallbackName?: string
|
||||
) {
|
||||
const acceleratable = spec.acceleratable;
|
||||
|
||||
const cpuManufacturer = acceleratable
|
||||
@@ -116,7 +129,9 @@ function getInstanceDerived(item: InstanceTypeItemModel) {
|
||||
acceleratable,
|
||||
isGPU: acceleratable,
|
||||
manufacturer: acceleratable ? spec.manufacturer || '' : 'cpu', // GPU manufacturer or 'cpu' for non-acceleratable types
|
||||
displayName: acceleratable ? spec.product || item.name : 'CPU-only',
|
||||
displayName: acceleratable
|
||||
? spec.displayName || spec.product || fallbackName
|
||||
: spec.displayName || 'CPU-only',
|
||||
ramUnit: spec.unitResourcesParsed?.ram?.value,
|
||||
os: _.capitalize(spec.os) || '',
|
||||
arch: spec.arch,
|
||||
@@ -159,9 +174,7 @@ export const InstanceMetadataSection: React.FC<MetadataSectionProps> = ({
|
||||
}) => {
|
||||
const intl = useIntl();
|
||||
|
||||
const { ramUnit, cpuUnitCores, isGPU, arch } = getInstanceDerived({
|
||||
spec
|
||||
} as InstanceTypeItemModel);
|
||||
const { ramUnit, cpuUnitCores, isGPU, arch } = getInstanceDerived(spec);
|
||||
|
||||
// Sliceable types append a "Sliceable {n}%" cell to the second row.
|
||||
const showSliceable = !!spec.sliceable && (slicedMaxPercentage ?? 0) > 0;
|
||||
@@ -217,10 +230,12 @@ const InstanceTypeItem: React.FC<InstanceTypeItemProps> = ({
|
||||
item,
|
||||
action
|
||||
}) => {
|
||||
const specData = item.spec || {};
|
||||
// Fold the live (API-shaped) item into the flat display model: definition
|
||||
// fields from spec, observed hardware from status.detail.
|
||||
const specData = buildInstanceTypeSnapshotSpec(item);
|
||||
|
||||
const { acceleratable, manufacturer, displayName, cpuManufacturer } =
|
||||
getInstanceDerived(item);
|
||||
getInstanceDerived(specData, item.name);
|
||||
|
||||
const manufacturerColor = manufactureColorMap[manufacturer] ?? 'purple';
|
||||
const showManufacturerTag = acceleratable && !!manufacturer;
|
||||
|
||||
@@ -3,7 +3,15 @@ import { StatusType } from '@/config/types';
|
||||
import { IconFont, icons } from '@gpustack/core-ui';
|
||||
import _ from 'lodash';
|
||||
import React from 'react';
|
||||
import { ListItem } from '../config/types';
|
||||
import { AcceleratorSlicedDetail, ListItem } from '../config/types';
|
||||
|
||||
// Whether a type can be sliced, per the API contract (replaces the removed
|
||||
// `spec.sliceable` boolean): logical (soft) slicing reports per-card capacity
|
||||
// or physical (e.g. MIG) profiles exist. Every level of slicedDetail may be
|
||||
// absent (exclude_none responses).
|
||||
export const isSliceableDetail = (detail?: AcceleratorSlicedDetail | null) =>
|
||||
(detail?.logical?.count ?? 0) > 0 ||
|
||||
(detail?.physical?.profiles?.length ?? 0) > 0;
|
||||
|
||||
export const InstanceStatusValueMap = {
|
||||
Scheduling: 'Scheduling',
|
||||
@@ -251,7 +259,7 @@ const parseQuantity = (value?: string | null): number => {
|
||||
// Returns the slider max for the accelerator count: the largest
|
||||
// tier.onceMaxRequest.accelerator across all tiers (not from candidates).
|
||||
export const getAcceleratorMax = (
|
||||
tiers?: { onceMaxRequest: { accelerator?: string } }[] | null
|
||||
tiers?: { onceMaxRequest: { accelerator?: string | null } }[] | null
|
||||
) => {
|
||||
if (!tiers?.length) return 0;
|
||||
return tiers.reduce((acc, tier) => {
|
||||
@@ -277,7 +285,10 @@ export const pickCandidateForAccelerator = <
|
||||
>(
|
||||
tiers:
|
||||
| {
|
||||
onceMaxRequest: { accelerator?: string; acceleratorSliced?: string };
|
||||
onceMaxRequest: {
|
||||
accelerator?: string | null;
|
||||
acceleratorSliced?: string | null;
|
||||
};
|
||||
candidates?: C[] | null;
|
||||
}[]
|
||||
| undefined
|
||||
|
||||
@@ -1,247 +0,0 @@
|
||||
export default {
|
||||
items: [
|
||||
{
|
||||
name: 'gpustack--nvidia-a10g-linux-amd64',
|
||||
spec: {
|
||||
memory: '24Gi',
|
||||
cores: '10240',
|
||||
sliceable: true,
|
||||
cpu: {
|
||||
cache: {}
|
||||
},
|
||||
cache: {},
|
||||
displayName: 'NVIDIA-A10G',
|
||||
acceleratorGroup: 'nvidia-a10g',
|
||||
generalGroup: 'generic',
|
||||
acceleratable: true,
|
||||
manufacturer: 'nvidia',
|
||||
product: 'NVIDIA-A10G',
|
||||
family: 'Ampere',
|
||||
os: 'linux',
|
||||
arch: 'amd64',
|
||||
unitResources: {
|
||||
cpu: '4',
|
||||
ram: '16Gi'
|
||||
},
|
||||
localStorage: '100Gi'
|
||||
},
|
||||
status: {
|
||||
onceMaxRequest: {
|
||||
accelerator: '1',
|
||||
acceleratorShared: '10',
|
||||
acceleratorSliced: '100',
|
||||
cpu: '0'
|
||||
},
|
||||
remaining: {
|
||||
accelerator: '1',
|
||||
acceleratorShared: '10',
|
||||
acceleratorSliced: '100',
|
||||
cpu: '0'
|
||||
},
|
||||
tiers: [
|
||||
{
|
||||
onceMaxRequest: {
|
||||
accelerator: '1',
|
||||
acceleratorShared: '10',
|
||||
acceleratorSliced: '100',
|
||||
cpu: '0'
|
||||
},
|
||||
remaining: {
|
||||
accelerator: '1',
|
||||
acceleratorShared: '10',
|
||||
acceleratorSliced: '100',
|
||||
cpu: '0'
|
||||
},
|
||||
candidates: [
|
||||
{
|
||||
cluster: '1',
|
||||
name: 'gpustack--nvidia-a10g-linux-amd64',
|
||||
phase: 'Active',
|
||||
accelerator: {
|
||||
onceMaxRequest: '1',
|
||||
remaining: '1',
|
||||
capacity: '1'
|
||||
},
|
||||
acceleratorShared: {
|
||||
onceMaxRequest: '10',
|
||||
remaining: '10',
|
||||
capacity: '10'
|
||||
},
|
||||
acceleratorSliced: {
|
||||
onceMaxRequest: '100',
|
||||
remaining: '100',
|
||||
capacity: '100'
|
||||
},
|
||||
cpu: {
|
||||
onceMaxRequest: '0',
|
||||
remaining: '0',
|
||||
capacity: '0'
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
name: 'gpustack--nvidia-tesla-t4-linux-amd64',
|
||||
spec: {
|
||||
memory: '16Gi',
|
||||
cores: '2560',
|
||||
sliceable: true,
|
||||
cpu: {
|
||||
cache: {}
|
||||
},
|
||||
cache: {},
|
||||
displayName: 'Tesla-T4',
|
||||
acceleratorGroup: 'nvidia-tesla-t4',
|
||||
generalGroup: 'generic',
|
||||
acceleratable: true,
|
||||
manufacturer: 'nvidia',
|
||||
product: 'Tesla-T4',
|
||||
family: 'Turing',
|
||||
os: 'linux',
|
||||
arch: 'amd64',
|
||||
unitResources: {
|
||||
cpu: '4',
|
||||
ram: '16Gi'
|
||||
},
|
||||
localStorage: '100Gi'
|
||||
},
|
||||
status: {
|
||||
onceMaxRequest: {
|
||||
accelerator: '0',
|
||||
acceleratorShared: '0',
|
||||
acceleratorSliced: '0',
|
||||
cpu: '0'
|
||||
},
|
||||
remaining: {
|
||||
accelerator: '0',
|
||||
acceleratorShared: '0',
|
||||
acceleratorSliced: '0',
|
||||
cpu: '0'
|
||||
},
|
||||
tiers: [
|
||||
{
|
||||
onceMaxRequest: {
|
||||
accelerator: '0',
|
||||
acceleratorShared: '0',
|
||||
acceleratorSliced: '0',
|
||||
cpu: '0'
|
||||
},
|
||||
remaining: {
|
||||
accelerator: '0',
|
||||
acceleratorShared: '0',
|
||||
acceleratorSliced: '0',
|
||||
cpu: '0'
|
||||
},
|
||||
candidates: [
|
||||
{
|
||||
cluster: '1',
|
||||
name: 'gpustack--nvidia-tesla-t4-linux-amd64',
|
||||
phase: 'Active',
|
||||
accelerator: {
|
||||
onceMaxRequest: '0',
|
||||
remaining: '0',
|
||||
capacity: '1'
|
||||
},
|
||||
acceleratorShared: {
|
||||
onceMaxRequest: '0',
|
||||
remaining: '0',
|
||||
capacity: '10'
|
||||
},
|
||||
acceleratorSliced: {
|
||||
onceMaxRequest: '0',
|
||||
remaining: '0',
|
||||
capacity: '100'
|
||||
},
|
||||
cpu: {
|
||||
onceMaxRequest: '0',
|
||||
remaining: '0',
|
||||
capacity: '0'
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
name: 'gpustack--generic-linux-amd64',
|
||||
spec: {
|
||||
sliceable: false,
|
||||
cpu: {
|
||||
cache: {}
|
||||
},
|
||||
cache: {},
|
||||
displayName: 'CPU-only',
|
||||
generalGroup: 'generic',
|
||||
acceleratable: false,
|
||||
os: 'linux',
|
||||
arch: 'amd64',
|
||||
unitResources: {
|
||||
cpu: '1',
|
||||
ram: '2Gi'
|
||||
},
|
||||
localStorage: '100Gi'
|
||||
},
|
||||
status: {
|
||||
onceMaxRequest: {
|
||||
accelerator: '0',
|
||||
acceleratorShared: '0',
|
||||
acceleratorSliced: '0',
|
||||
cpu: '16'
|
||||
},
|
||||
remaining: {
|
||||
accelerator: '0',
|
||||
acceleratorShared: '0',
|
||||
acceleratorSliced: '0',
|
||||
cpu: '23'
|
||||
},
|
||||
tiers: [
|
||||
{
|
||||
onceMaxRequest: {
|
||||
accelerator: '0',
|
||||
acceleratorShared: '0',
|
||||
acceleratorSliced: '0',
|
||||
cpu: '16'
|
||||
},
|
||||
remaining: {
|
||||
accelerator: '0',
|
||||
acceleratorShared: '0',
|
||||
acceleratorSliced: '0',
|
||||
cpu: '23'
|
||||
},
|
||||
candidates: [
|
||||
{
|
||||
cluster: '1',
|
||||
name: 'gpustack--generic-linux-amd64',
|
||||
phase: 'Active',
|
||||
accelerator: {
|
||||
onceMaxRequest: '0',
|
||||
remaining: '0',
|
||||
capacity: '0'
|
||||
},
|
||||
acceleratorShared: {
|
||||
onceMaxRequest: '0',
|
||||
remaining: '0',
|
||||
capacity: '0'
|
||||
},
|
||||
acceleratorSliced: {
|
||||
onceMaxRequest: '0',
|
||||
remaining: '0',
|
||||
capacity: '0'
|
||||
},
|
||||
cpu: {
|
||||
onceMaxRequest: '16',
|
||||
remaining: '23',
|
||||
capacity: '24'
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
]
|
||||
};
|
||||
@@ -131,77 +131,129 @@ export interface InstanceTypeResource {
|
||||
export interface InstanceTypeCandidate {
|
||||
cluster: string;
|
||||
name: string;
|
||||
accelerator: InstanceTypeResource;
|
||||
cpu: InstanceTypeResource;
|
||||
accelerator?: InstanceTypeResource | null;
|
||||
cpu?: InstanceTypeResource | null;
|
||||
// Shared-mode available resource (not shown in the GPU Instance form).
|
||||
acceleratorShared: InstanceTypeResource;
|
||||
acceleratorShared?: InstanceTypeResource | null;
|
||||
// Sliced-mode available resource.
|
||||
acceleratorSliced: InstanceTypeResource;
|
||||
phase: 'Active' | 'Inactive' | 'Draining';
|
||||
acceleratorSliced?: InstanceTypeResource | null;
|
||||
// This candidate's sliced (partitioning) capability.
|
||||
acceleratorSlicedDetail?: AcceleratorSlicedDetail | null;
|
||||
phase?: 'Active' | 'Inactive' | 'Draining' | null;
|
||||
}
|
||||
|
||||
export interface InstanceTypeTierOnceMaxRequestResource {
|
||||
accelerator?: string;
|
||||
cpu: QuanityCPU;
|
||||
ram: QuanityMemory;
|
||||
localStorage: QuanityLocalStorage;
|
||||
// Per-mode maxima as plain number strings — the shape of the aggregated
|
||||
// status.onceMaxRequest / status.remaining AND of tier onceMaxRequest /
|
||||
// remaining (they are identical in the API). accelerator counts whole cards,
|
||||
// acceleratorShared / acceleratorSliced are percentages, cpu is cores. The
|
||||
// API carries no ram / localStorage here — RAM caps derive from
|
||||
// spec.unitResources, disk from spec.localStorage.
|
||||
export interface InstanceTypeOverviewResource {
|
||||
accelerator?: `${number}` | null;
|
||||
acceleratorShared?: `${number}` | null;
|
||||
acceleratorSliced?: `${number}` | null;
|
||||
cpu?: QuanityCPU | null;
|
||||
}
|
||||
|
||||
export interface InstanceTypeTier {
|
||||
onceMaxRequest: InstanceTypeTierOnceMaxRequestResource;
|
||||
onceMaxRequest: InstanceTypeOverviewResource;
|
||||
remaining?: InstanceTypeOverviewResource | null;
|
||||
// The tier's aggregated sliced (partitioning) capability.
|
||||
acceleratorSlicedDetail?: AcceleratorSlicedDetail | null;
|
||||
candidates?: InstanceTypeCandidate[] | null;
|
||||
}
|
||||
|
||||
export interface InstanceTypeOnceMaxRequestResource {
|
||||
accelerator?: `${number}` | null;
|
||||
cpu: QuanityCPU;
|
||||
ram: QuanityMemory;
|
||||
localStorage: QuanityLocalStorage;
|
||||
acceleratorShared: `${number}` | null;
|
||||
acceleratorSliced: `${number}` | null;
|
||||
}
|
||||
|
||||
export interface CPUCache {
|
||||
l1i: string;
|
||||
l1d: string;
|
||||
l2: string;
|
||||
l3: string;
|
||||
l1i?: string | null;
|
||||
l1d?: string | null;
|
||||
l2?: string | null;
|
||||
l3?: string | null;
|
||||
}
|
||||
|
||||
export interface CPUInfo {
|
||||
physicalCores: string;
|
||||
threadsPerPhysicalCore: string;
|
||||
logicalCores: string;
|
||||
stepping: string | null;
|
||||
clockSpeed: string | null;
|
||||
maxClockSpeed: string | null;
|
||||
cacheLine: string;
|
||||
cache: CPUCache;
|
||||
manufacturer: string;
|
||||
product: string;
|
||||
family: string;
|
||||
physicalCores?: string | null;
|
||||
threadsPerPhysicalCore?: string | null;
|
||||
logicalCores?: string | null;
|
||||
stepping?: string | null;
|
||||
clockSpeed?: string | null;
|
||||
maxClockSpeed?: string | null;
|
||||
cacheLine?: string | null;
|
||||
cache?: CPUCache | null;
|
||||
manufacturer?: string | null;
|
||||
product?: string | null;
|
||||
family?: string | null;
|
||||
}
|
||||
|
||||
export interface InstanceTypeSpec {
|
||||
group: string;
|
||||
acceleratable: boolean;
|
||||
manufacturer: string;
|
||||
// Sliced (partitioning) capability descriptor. Replaces the removed
|
||||
// `spec.sliceable` boolean: a type is sliceable when logical (soft) slicing
|
||||
// reports capacity or physical (e.g. MIG) profiles exist — see
|
||||
// isSliceableDetail in ./index. Appears as status.detail.slicedDetail and as
|
||||
// tier / candidate `acceleratorSlicedDetail` in the aggregated view.
|
||||
export interface AcceleratorSlicedLogicalDetail {
|
||||
coresPercentageOvercommit?: boolean;
|
||||
// Max soft slices per card; 0 → soft slicing unsupported.
|
||||
count?: number | null;
|
||||
}
|
||||
|
||||
export interface AcceleratorSlicedPhysicalDetailProfile {
|
||||
name?: string | null;
|
||||
count?: number | null;
|
||||
}
|
||||
|
||||
export interface AcceleratorSlicedPhysicalDetail {
|
||||
profiles?: AcceleratorSlicedPhysicalDetailProfile[] | null;
|
||||
count?: number | null;
|
||||
}
|
||||
|
||||
export interface AcceleratorSlicedDetail {
|
||||
logical?: AcceleratorSlicedLogicalDetail | null;
|
||||
physical?: AcceleratorSlicedPhysicalDetail | null;
|
||||
}
|
||||
|
||||
// status.detail — the observed hardware descriptor. The API moved these off
|
||||
// spec (spec keeps user-defined fields only). The whole object is absent until
|
||||
// the operator backfills status, and every response is exclude_none — treat
|
||||
// every key as possibly missing.
|
||||
export interface InstanceTypeDetail {
|
||||
// Device identity.
|
||||
manufacturer?: string | null;
|
||||
product?: string | null;
|
||||
memory?: string | null;
|
||||
family?: string | null;
|
||||
// Host node CPU (flat fields, as opposed to the nested `cpu` below).
|
||||
physicalCores?: string | null;
|
||||
threadsPerPhysicalCore?: string | null;
|
||||
logicalCores?: string | null;
|
||||
stepping?: string | null;
|
||||
clockSpeed?: string | null;
|
||||
maxClockSpeed?: string | null;
|
||||
cacheLine?: string | null;
|
||||
cache?: CPUCache | null;
|
||||
// Accelerator hardware.
|
||||
memory?: string | null;
|
||||
cores?: string | null;
|
||||
computeCapability?: string | null;
|
||||
sliced?: string | null;
|
||||
sliceable?: boolean;
|
||||
slicedDetail?: AcceleratorSlicedDetail | null;
|
||||
// The accelerator's own CPU (distinct from the flat host CPU fields above).
|
||||
cpu?: CPUInfo | null;
|
||||
}
|
||||
|
||||
// Mirrors the API spec object exactly (user-defined fields only — observed
|
||||
// hardware lives on status.detail), plus two UI-computed enrichments filled by
|
||||
// use-query-instance-types whose names exist nowhere in the API.
|
||||
export interface InstanceTypeSpec {
|
||||
displayName?: string | null;
|
||||
acceleratorGroup?: string | null;
|
||||
generalGroup?: string | null;
|
||||
acceleratable?: boolean;
|
||||
os?: string;
|
||||
arch?: string;
|
||||
localStorage?: QuanityLocalStorage;
|
||||
maxComputeUnitCount?: number;
|
||||
unitResources?: {
|
||||
cpu: QuanityCPU;
|
||||
ram: QuanityMemory;
|
||||
};
|
||||
os?: string;
|
||||
arch?: string;
|
||||
cpu?: CPUInfo;
|
||||
cache?: Record<string, string>;
|
||||
// ---- UI-computed (not part of the API contract) ----
|
||||
// spec.unitResources parsed to numbers.
|
||||
unitResourcesParsed?: {
|
||||
cpu: {
|
||||
cores?: number;
|
||||
@@ -214,10 +266,31 @@ export interface InstanceTypeSpec {
|
||||
num: number;
|
||||
} | null;
|
||||
};
|
||||
// Max requestable unit (card / core) count, derived from status.
|
||||
maxComputeUnitCount?: number;
|
||||
}
|
||||
|
||||
// Flat spec snapshot persisted in a GPU instance's `description` field at
|
||||
// create time (see utils/instance-description.ts) and reused as the display
|
||||
// model of the type card / metadata section. It merges the definition spec
|
||||
// with the observed hardware from status.detail and the derived `sliceable`.
|
||||
// The flat shape is a UI document format — do NOT confuse it with the API
|
||||
// InstanceTypeSpec; it stays flat for compatibility with snapshots persisted
|
||||
// by older instances.
|
||||
export interface InstanceTypeSnapshotSpec extends InstanceTypeSpec {
|
||||
manufacturer?: string | null;
|
||||
product?: string | null;
|
||||
family?: string | null;
|
||||
memory?: string | null;
|
||||
sliceable?: boolean;
|
||||
// Accelerator CPU identity only (from status.detail.cpu).
|
||||
cpu?: Pick<CPUInfo, 'manufacturer' | 'product' | 'family'> | null;
|
||||
}
|
||||
|
||||
export interface InstanceTypeStatus {
|
||||
onceMaxRequest: InstanceTypeOnceMaxRequestResource;
|
||||
detail?: InstanceTypeDetail | null;
|
||||
onceMaxRequest: InstanceTypeOverviewResource;
|
||||
remaining?: InstanceTypeOverviewResource | null;
|
||||
tiers?: InstanceTypeTier[] | null;
|
||||
}
|
||||
|
||||
|
||||
@@ -35,7 +35,11 @@ import { DefaultImagePullPolicy } from '../../templates/config';
|
||||
import TemplateBasicForm, {
|
||||
BasicResourceMax
|
||||
} from '../../templates/forms/basic';
|
||||
import { pickCandidateForAccelerator, StorageModeValueMap } from '../config';
|
||||
import {
|
||||
isSliceableDetail,
|
||||
pickCandidateForAccelerator,
|
||||
StorageModeValueMap
|
||||
} from '../config';
|
||||
import { FormContext } from '../config/form-context';
|
||||
import { FormData, InstanceTypeItem, ListItem } from '../config/types';
|
||||
import instanceStyles from '../styles/instances.module.less';
|
||||
@@ -289,15 +293,15 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
|
||||
const wholeFactor = isGPUType ? accelerator : cpuCount;
|
||||
|
||||
// Sliced mode: scale a single card's unit resources by the chosen
|
||||
// percentage. Scale CPU in millicores and RAM in MiB so fractional
|
||||
// slices stay precise and k8s-valid (integers) — e.g. 10% of a 4-core /
|
||||
// 16Gi card → 400m / 1638Mi, not a rounded-up 1 core / 1Gi.
|
||||
// percentage, submitted as whole cores / whole Gi (floored, min 1) so
|
||||
// the payload matches what the disabled CPU / RAM inputs display —
|
||||
// e.g. 10% of a 4-core / 16Gi card → "1" / "1Gi".
|
||||
if (sliced && unitResourcesParsed) {
|
||||
const cpuCores = unitResourcesParsed.cpu?.cores ?? 0;
|
||||
const ramValue = unitResourcesParsed.ram?.value ?? 0;
|
||||
return {
|
||||
cpu: `${Math.max(1, _.floor((cpuCores * 1000 * percentage) / 100))}m`,
|
||||
ram: `${Math.max(1, _.floor((ramValue * 1024 * percentage) / 100))}Mi`
|
||||
cpu: `${Math.max(1, _.floor((cpuCores * percentage) / 100))}`,
|
||||
ram: `${Math.max(1, _.floor((ramValue * percentage) / 100))}Gi`
|
||||
};
|
||||
}
|
||||
|
||||
@@ -335,24 +339,34 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
|
||||
form.setFieldsValue({
|
||||
spec: {
|
||||
resources: {
|
||||
// Floor the scaled unit resources to whole units; CPU never drops
|
||||
// below 1 core so a small slice still gets a usable vCPU.
|
||||
// Floor the scaled unit resources to whole units, never below 1 —
|
||||
// a small slice (e.g. 8 GB × 10%) still shows a usable 1 vCPU /
|
||||
// 1 GB instead of 0. Display-only: the submit path recomputes
|
||||
// both precisely in millicores / Mi.
|
||||
cpu:
|
||||
cpuCores != null && percentage > 0
|
||||
? Math.max(1, _.floor((cpuCores * percentage) / 100))
|
||||
: null,
|
||||
ram:
|
||||
ramValue != null && percentage > 0
|
||||
? _.floor((ramValue * percentage) / 100)
|
||||
? Math.max(1, _.floor((ramValue * percentage) / 100))
|
||||
: null
|
||||
}
|
||||
}
|
||||
} as any);
|
||||
};
|
||||
|
||||
// Whether the selected type allows the compute (cores) ratio to exceed
|
||||
// the memory ratio. Without overcommit there is no cores selector and the
|
||||
// cores ratio is locked to (mirrors) the memory ratio.
|
||||
const coresOvercommit =
|
||||
!!selectedInstanceType?.status?.detail?.slicedDetail?.logical
|
||||
?.coresPercentageOvercommit;
|
||||
|
||||
// Single entry point for the sliced memory ratio: write the ratio and
|
||||
// rescale CPU / RAM off it. The compute (cores) ratio must stay >= memory,
|
||||
// so bump it up when memory overtakes it. Reused by the slider onChange.
|
||||
// rescale CPU / RAM off it. With cores overcommit the compute ratio must
|
||||
// stay >= memory (bump it up when memory overtakes it); without it the
|
||||
// compute ratio always mirrors memory. Reused by the slider onChange.
|
||||
const applySliceMemoryPercentage = (value: number) => {
|
||||
const currentCores = _.toNumber(
|
||||
form.getFieldValue([
|
||||
@@ -361,7 +375,9 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
|
||||
'acceleratorSlicedCoresPercentage'
|
||||
])
|
||||
);
|
||||
const coresPercentage = currentCores >= value ? currentCores : value;
|
||||
const coresPercentage = coresOvercommit
|
||||
? Math.max(currentCores, value)
|
||||
: value;
|
||||
form.setFieldsValue({
|
||||
spec: {
|
||||
resources: {
|
||||
@@ -422,12 +438,14 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
|
||||
|
||||
console.log('picked candidate', candidate, instanceType, count);
|
||||
|
||||
// The API carries no RAM max on onceMaxRequest — derive it from the
|
||||
// per-unit RAM × the max requestable unit count (RAM always scales with
|
||||
// the unit count). Disk max comes from spec.localStorage (UI-only cap).
|
||||
const unitRamGi = instanceType.spec?.unitResourcesParsed?.ram?.value;
|
||||
const maxUnits = instanceType.spec?.maxComputeUnitCount || 0;
|
||||
setOnceMaxRequest({
|
||||
cpu: ceilMilliToCore(candidate?.cpu?.onceMaxRequest)?.cores,
|
||||
// candidate no longer carries ram/localStorage: memory max comes from
|
||||
// the type-level onceMaxRequest.ram (already parsed to a Gi number by
|
||||
// the query hook), disk max from spec.localStorage (UI-only cap).
|
||||
memory: _.toNumber(instanceType.status?.onceMaxRequest?.ram) || null,
|
||||
memory: unitRamGi && maxUnits ? unitRamGi * maxUnits : null,
|
||||
localStorage:
|
||||
parseQuantityToGi(instanceType.spec?.localStorage)?.value ?? null
|
||||
});
|
||||
@@ -513,7 +531,9 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
|
||||
const slicedMax =
|
||||
_.toNumber(instanceType.status?.onceMaxRequest?.acceleratorSliced) || 0;
|
||||
const defaultSliced =
|
||||
!!instanceType.spec?.sliceable && wholeMax < 1 && slicedMax > 0;
|
||||
isSliceableDetail(instanceType.status?.detail?.slicedDetail) &&
|
||||
wholeMax < 1 &&
|
||||
slicedMax > 0;
|
||||
|
||||
if (defaultSliced) {
|
||||
setSliceMode('sliced');
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
import { PageAction } from '@/config';
|
||||
import { PageActionType } from '@/config/types';
|
||||
import NumberSelection from '@/pages/_components/number-selection';
|
||||
import { InputNumber, LabelInfo } from '@gpustack/core-ui';
|
||||
import { InputNumber } from '@gpustack/core-ui';
|
||||
import { useIntl } from '@umijs/max';
|
||||
import { Divider, Flex, Form, Segmented } from 'antd';
|
||||
import { Flex, Form, Segmented } from 'antd';
|
||||
import _ from 'lodash';
|
||||
import { useContext, useMemo } from 'react';
|
||||
import styled from 'styled-components';
|
||||
@@ -12,6 +12,7 @@ import { parseJsonSafe } from '../../utils';
|
||||
import InstanceTypeItem, {
|
||||
InstanceMetadataSection
|
||||
} from '../components/instance-type-item';
|
||||
import { isSliceableDetail } from '../config';
|
||||
import { FormContext } from '../config/form-context';
|
||||
import {
|
||||
FormData,
|
||||
@@ -60,6 +61,21 @@ const InstanceTypePicker: React.FC<InstanceTypePickerProps> = ({
|
||||
// Fixed 10-tick percentage scale (10..100) for the sliced (percentage) mode.
|
||||
const SLICE_PERCENT_TICKS = [10, 20, 30, 50];
|
||||
|
||||
// The paired VRAM + Compute selectors (cores overcommit) are grouped in a
|
||||
// bordered card; a lone "Percentage" selector (no overcommit) renders bare so
|
||||
// it matches the whole-card GPU Count block's styling.
|
||||
const SliceFieldWrapper: React.FC<{
|
||||
withCard: boolean;
|
||||
children: React.ReactNode;
|
||||
}> = ({ withCard, children }) =>
|
||||
withCard ? (
|
||||
<FieldBlock>
|
||||
<SelectedCard style={{ padding: 0 }}>{children}</SelectedCard>
|
||||
</FieldBlock>
|
||||
) : (
|
||||
<>{children}</>
|
||||
);
|
||||
|
||||
interface InstanceTypeFormItemProps {
|
||||
action: PageActionType;
|
||||
disabled?: boolean;
|
||||
@@ -115,13 +131,6 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
|
||||
return selectedInstanceType?.spec?.maxComputeUnitCount || 0;
|
||||
}, [readonlyType, currentData, selectedInstanceType]);
|
||||
|
||||
const isGPU = useMemo(() => {
|
||||
if (readonlyType) {
|
||||
return _.toNumber(currentData?.spec?.resources?.accelerator) > 0;
|
||||
}
|
||||
return selectedInstanceType?.spec?.acceleratable;
|
||||
}, [selectedInstanceType, readonlyType, currentData]);
|
||||
|
||||
const handleOnGPUCountChange = (value: number) => {
|
||||
onGPUCountChange?.(value);
|
||||
};
|
||||
@@ -130,7 +139,9 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
|
||||
// the section is editable (create / recreate, or edit after re-picking a
|
||||
// type; a not-yet-re-typed edit renders a readonly card).
|
||||
const showModeSwitch =
|
||||
!readonlyType && isGPUType && !!selectedInstanceType?.spec?.sliceable;
|
||||
!readonlyType &&
|
||||
isGPUType &&
|
||||
isSliceableDetail(selectedInstanceType?.status?.detail?.slicedDetail);
|
||||
|
||||
const handleModeChange = (value: string) => {
|
||||
onSliceModeChange?.(value as 'whole' | 'sliced');
|
||||
@@ -164,10 +175,17 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
|
||||
selectedInstanceType?.status?.onceMaxRequest?.acceleratorSliced
|
||||
) || 0;
|
||||
|
||||
// Whether the compute (cores) ratio may exceed the memory ratio. When the
|
||||
// type doesn't support overcommit, cores are locked to the memory ratio —
|
||||
// no cores selector, and the memory selector reads as a plain "Percentage".
|
||||
const coresOvercommit =
|
||||
!!selectedInstanceType?.status?.detail?.slicedDetail?.logical
|
||||
?.coresPercentageOvercommit;
|
||||
|
||||
const modeSegmented = showModeSwitch ? (
|
||||
<Segmented
|
||||
size="small"
|
||||
shape="round"
|
||||
size="middle"
|
||||
type="rounded"
|
||||
style={{ fontSize: 12 }}
|
||||
value={sliceMode}
|
||||
disabled={disabled}
|
||||
@@ -191,7 +209,7 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
|
||||
|
||||
// When the max ratio is below 10%, switch the ticks to a finer 1..10 scale
|
||||
// so small slices are still selectable; otherwise use the 10..100 scale.
|
||||
const sliceTicks =
|
||||
const sliceTicks: number[] =
|
||||
slicedMaxPercentage < 10
|
||||
? [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
|
||||
: SLICE_PERCENT_TICKS;
|
||||
@@ -246,8 +264,8 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
|
||||
}}
|
||||
>
|
||||
{description.acceleratable
|
||||
? `${description.product} x ${currentData?.spec?.resources?.accelerator}`
|
||||
: 'CPU'}
|
||||
? `${description.displayName || description.product} x ${currentData?.spec?.resources?.accelerator}`
|
||||
: description.displayName || 'CPU'}
|
||||
</span>
|
||||
<InstanceMetadataSection spec={description}></InstanceMetadataSection>
|
||||
</Flex>
|
||||
@@ -292,9 +310,7 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
|
||||
</FieldBlock>
|
||||
{showModeSwitch && (
|
||||
<div>
|
||||
<LabelInfo label={intl.formatMessage({ id: 'models.form.mode' })} />
|
||||
<div style={{ marginTop: 8 }}>{modeSegmented}</div>
|
||||
<Divider />
|
||||
<div style={{ marginBlock: 8 }}>{modeSegmented}</div>
|
||||
</div>
|
||||
)}
|
||||
{!noAvailableTypes && (
|
||||
@@ -358,10 +374,13 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
|
||||
</Form.Item>
|
||||
)}
|
||||
{!noAvailableTypes && isSliced && (
|
||||
<FieldBlock>
|
||||
<SelectedCard>
|
||||
<SliceFieldWrapper withCard={coresOvercommit}>
|
||||
<>
|
||||
<Form.Item<FormData>
|
||||
name={['spec', 'resources', 'acceleratorSlicedMemoryPercentage']}
|
||||
// Grouped with the compute selector inside one card — tighten
|
||||
// the default 24px gap between the pair.
|
||||
style={coresOvercommit ? { marginBottom: 0 } : undefined}
|
||||
getValueProps={(value) => ({
|
||||
value: value != null ? _.toNumber(value) : undefined
|
||||
})}
|
||||
@@ -405,68 +424,87 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
|
||||
alwaysShowInput
|
||||
required
|
||||
disabled={disabled}
|
||||
style={{ border: 'none' }}
|
||||
// Inside the card the selector drops its own border; the bare
|
||||
// (no-overcommit) variant keeps it, like the GPU Count block.
|
||||
style={coresOvercommit ? { border: 'none' } : undefined}
|
||||
onChange={handleMemoryPercentageChange}
|
||||
label={intl.formatMessage({
|
||||
id: 'gpuservice.instance.slice.memoryPercentage'
|
||||
// Without cores overcommit this single ratio drives both
|
||||
// VRAM and compute, so drop the "VRAM" qualifier.
|
||||
id: coresOvercommit
|
||||
? 'gpuservice.instance.slice.memoryPercentage'
|
||||
: 'gpuservice.instance.slice.percentage'
|
||||
})}
|
||||
/>
|
||||
</Form.Item>
|
||||
{/* Compute (cores) percentage. Fixed 10..100 ticks; ticks below the
|
||||
chosen memory ratio are disabled (cores must be >= memory). */}
|
||||
<Form.Item<FormData>
|
||||
name={['spec', 'resources', 'acceleratorSlicedCoresPercentage']}
|
||||
style={{ marginBottom: 0 }}
|
||||
getValueProps={(value) => ({
|
||||
value: value != null ? _.toNumber(value) : undefined
|
||||
})}
|
||||
rules={[
|
||||
{
|
||||
required: true,
|
||||
validator: (_, value) => {
|
||||
const num = Number(value);
|
||||
if (value == null || value === '' || Number.isNaN(num)) {
|
||||
return Promise.reject(
|
||||
new Error(
|
||||
intl.formatMessage({
|
||||
id: 'gpuservice.instance.slice.percentage.required'
|
||||
})
|
||||
)
|
||||
);
|
||||
}
|
||||
if (num < slicedMemoryPercentage || num > 100) {
|
||||
return Promise.reject(
|
||||
new Error(
|
||||
intl.formatMessage(
|
||||
{ id: 'gpuservice.instance.slice.cores.min' },
|
||||
{ count: slicedMemoryPercentage }
|
||||
)
|
||||
)
|
||||
);
|
||||
}
|
||||
return Promise.resolve();
|
||||
}
|
||||
}
|
||||
]}
|
||||
>
|
||||
<NumberSelection
|
||||
min={slicedMemoryPercentage}
|
||||
max={100}
|
||||
step={10}
|
||||
maxCount={SLICE_PERCENT_TICKS.length}
|
||||
presetValues={SLICE_PERCENT_TICKS}
|
||||
alwaysShowInput
|
||||
required
|
||||
disabled={disabled}
|
||||
onChange={handleCoresPercentageChange}
|
||||
style={{ border: 'none' }}
|
||||
label={intl.formatMessage({
|
||||
id: 'gpuservice.instance.slice.coresPercentage'
|
||||
chosen memory ratio are disabled (cores must be >= memory). Only
|
||||
types with cores overcommit get the selector — without it the
|
||||
ratio is locked to the memory percentage (the parent mirrors it),
|
||||
carried by a hidden field so it still rides the submit. */}
|
||||
{coresOvercommit ? (
|
||||
<Form.Item<FormData>
|
||||
name={['spec', 'resources', 'acceleratorSlicedCoresPercentage']}
|
||||
style={{ marginBottom: 0 }}
|
||||
getValueProps={(value) => ({
|
||||
value: value != null ? _.toNumber(value) : undefined
|
||||
})}
|
||||
/>
|
||||
</Form.Item>
|
||||
</SelectedCard>
|
||||
</FieldBlock>
|
||||
rules={[
|
||||
{
|
||||
required: true,
|
||||
validator: (_, value) => {
|
||||
const num = Number(value);
|
||||
if (value == null || value === '' || Number.isNaN(num)) {
|
||||
return Promise.reject(
|
||||
new Error(
|
||||
intl.formatMessage({
|
||||
id: 'gpuservice.instance.slice.percentage.required'
|
||||
})
|
||||
)
|
||||
);
|
||||
}
|
||||
if (num < slicedMemoryPercentage || num > 100) {
|
||||
return Promise.reject(
|
||||
new Error(
|
||||
intl.formatMessage(
|
||||
{ id: 'gpuservice.instance.slice.cores.min' },
|
||||
{ count: slicedMemoryPercentage }
|
||||
)
|
||||
)
|
||||
);
|
||||
}
|
||||
return Promise.resolve();
|
||||
}
|
||||
}
|
||||
]}
|
||||
>
|
||||
<NumberSelection
|
||||
min={slicedMemoryPercentage}
|
||||
max={100}
|
||||
step={10}
|
||||
maxCount={SLICE_PERCENT_TICKS.length}
|
||||
presetValues={SLICE_PERCENT_TICKS}
|
||||
alwaysShowInput
|
||||
required
|
||||
disabled={disabled}
|
||||
onChange={handleCoresPercentageChange}
|
||||
style={{ border: 'none' }}
|
||||
label={intl.formatMessage({
|
||||
id: 'gpuservice.instance.slice.coresPercentage'
|
||||
})}
|
||||
/>
|
||||
</Form.Item>
|
||||
) : (
|
||||
<Form.Item<FormData>
|
||||
name={['spec', 'resources', 'acceleratorSlicedCoresPercentage']}
|
||||
style={{ marginBottom: 0 }}
|
||||
hidden
|
||||
>
|
||||
<InputNumber />
|
||||
</Form.Item>
|
||||
)}
|
||||
</>
|
||||
</SliceFieldWrapper>
|
||||
)}
|
||||
{/* A not-yet-re-typed edit renders a readonly card (no sliced UI), so
|
||||
register the slice percentages as hidden fields — otherwise their
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
import { useQueryData } from '@gpustack/core-ui';
|
||||
import React from 'react';
|
||||
import { ceilMilliToCore, parseQuantityToGi } from '../../utils';
|
||||
import { getAcceleratorMax } from '../config';
|
||||
import mockInstanceTypes from '../config/mock-data';
|
||||
import { queryGPUServiceInstanceTypes } from '../apis';
|
||||
import { getAcceleratorMax, isSliceableDetail } from '../config';
|
||||
import { InstanceTypeItem } from '../config/types';
|
||||
|
||||
type InstanceType = InstanceTypeItem & {
|
||||
@@ -13,7 +13,7 @@ export default function useQueryInstanceTypes() {
|
||||
const fetchDetail = (
|
||||
params: Global.SearchParams = { page: 1, perPage: 100 },
|
||||
options?: any
|
||||
) => Promise.resolve(mockInstanceTypes); // queryGPUServiceInstanceTypes(params, options);
|
||||
) => queryGPUServiceInstanceTypes(params, options);
|
||||
|
||||
const { detailData, loading, cancelRequest, fetchData } = useQueryData<
|
||||
Global.PageResponse<InstanceTypeItem>,
|
||||
@@ -40,7 +40,7 @@ export default function useQueryInstanceTypes() {
|
||||
// Sliceable types stay selectable as long as either whole-card or sliced
|
||||
// capacity remains; unavailable only when both status.onceMaxRequest
|
||||
// .accelerator and .acceleratorSliced are 0.
|
||||
if (item.spec?.sliceable) {
|
||||
if (isSliceableDetail(item.status?.detail?.slicedDetail)) {
|
||||
const wholeMax = Number(item.status?.onceMaxRequest?.accelerator) || 0;
|
||||
const slicedMax =
|
||||
Number(item.status?.onceMaxRequest?.acceleratorSliced) || 0;
|
||||
@@ -77,17 +77,11 @@ export default function useQueryInstanceTypes() {
|
||||
},
|
||||
status: {
|
||||
...item.status,
|
||||
// Normalize cpu (possibly millicores) to a whole-core count string;
|
||||
// the other onceMaxRequest fields are plain number strings already.
|
||||
onceMaxRequest: {
|
||||
...rawMax,
|
||||
cpu: rawMax?.cpu
|
||||
? `${ceilMilliToCore(rawMax.cpu)?.cores || 0}`
|
||||
: '',
|
||||
ram: rawMax?.ram
|
||||
? `${parseQuantityToGi(rawMax.ram)?.value || 0}`
|
||||
: '',
|
||||
localStorage: rawMax?.localStorage
|
||||
? `${parseQuantityToGi(rawMax.localStorage)?.value || 0}`
|
||||
: ''
|
||||
cpu: rawMax?.cpu ? `${ceilMilliToCore(rawMax.cpu)?.cores || 0}` : ''
|
||||
}
|
||||
},
|
||||
|
||||
|
||||
@@ -1,5 +1,25 @@
|
||||
import _ from 'lodash';
|
||||
import { InstanceTypeItem } from '../config/types';
|
||||
import { isSliceableDetail } from '../config';
|
||||
import { InstanceTypeItem, InstanceTypeSnapshotSpec } from '../config/types';
|
||||
|
||||
// Build the flat snapshot spec from a live (API-shaped) instance type:
|
||||
// definition fields from spec, observed hardware from status.detail, plus the
|
||||
// derived `sliceable`. This flat shape is the UI document format persisted in
|
||||
// the instance's `description` (older instances already carry it flat) and
|
||||
// doubles as the display model of the type card / metadata section.
|
||||
export const buildInstanceTypeSnapshotSpec = (
|
||||
instanceType: InstanceTypeItem
|
||||
): InstanceTypeSnapshotSpec => {
|
||||
const detail = instanceType.status?.detail;
|
||||
return {
|
||||
...instanceType.spec,
|
||||
..._.pick(detail, ['manufacturer', 'product', 'family', 'memory']),
|
||||
sliceable: isSliceableDetail(detail?.slicedDetail),
|
||||
// Accelerator CPU identity only — the full CPU descriptor is too bulky to
|
||||
// persist and the UI only shows who made it.
|
||||
cpu: _.pick(detail?.cpu, ['manufacturer', 'product', 'family'])
|
||||
};
|
||||
};
|
||||
|
||||
// Serialize the chosen instance type into the instance's `description` field —
|
||||
// a persisted spec snapshot the form reads back to render the type card and
|
||||
@@ -10,9 +30,6 @@ export const saveInstanceDataInDescription = (
|
||||
): string => {
|
||||
return JSON.stringify({
|
||||
name: instanceType.name,
|
||||
spec: {
|
||||
..._.omit(instanceType.spec, ['cache', 'cpu']),
|
||||
cpu: _.pick(instanceType.spec?.cpu, ['manufacturer', 'product', 'family'])
|
||||
}
|
||||
spec: buildInstanceTypeSnapshotSpec(instanceType)
|
||||
});
|
||||
};
|
||||
|
||||
@@ -11,10 +11,10 @@
|
||||
* with ``buildInstanceTypeRecordFromMiB`` and feed it here.
|
||||
*/
|
||||
import _ from 'lodash';
|
||||
import { parseJsonSafe, parseQuantityToGi } from '../../utils';
|
||||
import { ceilMilliToCore, parseJsonSafe, parseQuantityToGi } from '../../utils';
|
||||
import InstanceTypeCell from '../components/instance-type-cell';
|
||||
import { formatMemoryDisplay } from '../config';
|
||||
import { InstanceTypeSpec, ListItem } from '../config/types';
|
||||
import { InstanceTypeSnapshotSpec, ListItem } from '../config/types';
|
||||
|
||||
// Minimal shape of the ``useIntl()`` result we depend on — keeps this module
|
||||
// free of an intl package import.
|
||||
@@ -25,7 +25,7 @@ const toGB = (v?: string | number) =>
|
||||
|
||||
const buildResourcesData = (
|
||||
instanceType: {
|
||||
spec: InstanceTypeSpec;
|
||||
spec: InstanceTypeSnapshotSpec;
|
||||
},
|
||||
options: {
|
||||
count: number;
|
||||
@@ -54,7 +54,7 @@ const getSliceMemoryPercentage = (record: ListItem) =>
|
||||
_.toNumber(record.spec?.resources?.acceleratorSlicedMemoryPercentage) || 0;
|
||||
|
||||
const formatResources = (
|
||||
instanceTypeSpec: { spec: InstanceTypeSpec },
|
||||
instanceTypeSpec: { spec: InstanceTypeSnapshotSpec },
|
||||
record: ListItem
|
||||
) => {
|
||||
const resources = buildResourcesData(instanceTypeSpec, {
|
||||
@@ -77,25 +77,28 @@ const formatResources = (
|
||||
|
||||
const sliceMemoryPercentage = getSliceMemoryPercentage(record);
|
||||
|
||||
// Sliced: CPU / RAM carry the already-scaled values on spec.resources, and
|
||||
// VRAM is the per-card memory scaled by the memory percentage (floored,
|
||||
// min 1) — not the whole card's size.
|
||||
// Sliced: CPU / RAM carry the already-scaled values on spec.resources —
|
||||
// whole cores / whole Gi for instances created by the current form; parse
|
||||
// (instead of echoing the raw quantity) so legacy instances persisted as
|
||||
// millicores / Mi (e.g. "400m" / "1638Mi") render as whole units too. VRAM
|
||||
// is the per-card memory scaled by the memory percentage (floored, min 1) —
|
||||
// not the whole card's size.
|
||||
if (sliceMemoryPercentage > 0) {
|
||||
const vramGi = parseQuantityToGi(
|
||||
(instanceTypeSpec.spec as any)?.memory
|
||||
)?.value;
|
||||
const vramGi = parseQuantityToGi(instanceTypeSpec.spec?.memory)?.value;
|
||||
const vram =
|
||||
vramGi != null
|
||||
? `${Math.max(1, _.floor((vramGi * sliceMemoryPercentage) / 100))} GB`
|
||||
: undefined;
|
||||
const cpuCores = ceilMilliToCore(
|
||||
_.toString(record.spec?.resources?.cpu) || null
|
||||
)?.cores;
|
||||
const ramGi = parseQuantityToGi(
|
||||
_.toString(record.spec?.resources?.ram) || null
|
||||
)?.value;
|
||||
|
||||
return {
|
||||
cpu: record.spec?.resources?.cpu
|
||||
? `${record.spec?.resources?.cpu} vCPU`
|
||||
: '-',
|
||||
ram: record.spec?.resources?.ram
|
||||
? toGB(record.spec?.resources?.ram)
|
||||
: '-',
|
||||
cpu: cpuCores != null ? `${Math.max(1, cpuCores)} vCPU` : '-',
|
||||
ram: ramGi != null ? `${Math.max(1, ramGi)} GB` : '-',
|
||||
vram,
|
||||
localStorage: record.spec?.resources?.localStorage
|
||||
? toGB(record.spec?.resources?.localStorage)
|
||||
@@ -105,7 +108,7 @@ const formatResources = (
|
||||
|
||||
// VRAM = per-card GPU memory (a single card's size; not aggregated across
|
||||
// cards — the model's marquee spec).
|
||||
const vram = formatMemoryDisplay((instanceTypeSpec.spec as any)?.memory);
|
||||
const vram = formatMemoryDisplay(instanceTypeSpec.spec?.memory ?? undefined);
|
||||
|
||||
return {
|
||||
cpu: resources.cpu ? `${resources.cpu} vCPU` : '-',
|
||||
@@ -142,13 +145,17 @@ export const renderInstanceType = (
|
||||
const accelerator = record.spec?.resources?.accelerator;
|
||||
const sliceMemoryPercentage = getSliceMemoryPercentage(record);
|
||||
const isSliced = description.acceleratable && sliceMemoryPercentage > 0;
|
||||
// Type label (primary cell label and the popover's "Type" row) prefers the
|
||||
// user-defined displayName persisted in the description snapshot, falling
|
||||
// back to the hardware product.
|
||||
const typeLabel = description.displayName || description.product;
|
||||
const title =
|
||||
options.title ??
|
||||
(description.acceleratable
|
||||
? isSliced
|
||||
? `${description.product} (${sliceMemoryPercentage}%)`
|
||||
: `${description.product} x ${accelerator}`
|
||||
: 'CPU-only');
|
||||
? `${typeLabel} (${sliceMemoryPercentage}%)`
|
||||
: `${typeLabel} x ${accelerator}`
|
||||
: description.displayName || 'CPU-only');
|
||||
|
||||
const volume = (record.spec as any)?.volume;
|
||||
// Spec popover grouped by category (GPU / CPU / Memory / Disk), mirroring
|
||||
@@ -179,7 +186,7 @@ export const renderInstanceType = (
|
||||
],
|
||||
[
|
||||
intl.formatMessage({ id: 'gpuservice.instance.section.type' }),
|
||||
description.product
|
||||
typeLabel
|
||||
],
|
||||
[
|
||||
intl.formatMessage({ id: 'gpuservice.instance.memory' }),
|
||||
|
||||
Reference in New Issue
Block a user