@daocloud-proto/baize 0.111.2 → 0.111.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -238,6 +238,9 @@ export type SingleDatasetRequest = {
|
|
|
238
238
|
share?: boolean
|
|
239
239
|
sharedStoWorkspaces?: number[]
|
|
240
240
|
uri?: string
|
|
241
|
+
description?: string
|
|
242
|
+
labels?: {[key: string]: string}
|
|
243
|
+
annotations?: {[key: string]: string}
|
|
241
244
|
}
|
|
242
245
|
|
|
243
246
|
export type UpdateDatasetRequest = BaseUpdateDatasetRequest
|
|
@@ -184,6 +184,15 @@ export type NvidiaGPUGrafanaDashboardRequest = {
|
|
|
184
184
|
to?: string
|
|
185
185
|
}
|
|
186
186
|
|
|
187
|
+
export type GPUGrafanaDashboardRequest = {
|
|
188
|
+
vendor?: string
|
|
189
|
+
cluster?: string
|
|
190
|
+
node?: string
|
|
191
|
+
gpuIndex?: string
|
|
192
|
+
from?: string
|
|
193
|
+
to?: string
|
|
194
|
+
}
|
|
195
|
+
|
|
187
196
|
export class MetricsService {
|
|
188
197
|
static QueryMultipleVectors(req: QueryMultipleVectorRequest, initReq?: fm.InitReq): Promise<MultipleVectorQueryResponse> {
|
|
189
198
|
return fm.fetchReq<QueryMultipleVectorRequest, MultipleVectorQueryResponse>(`/apis/baize.io/v1alpha1/metrics/multiple-queries?${fm.renderURLSearchParams(req, [])}`, {...initReq, method: "GET"})
|
|
@@ -209,4 +218,7 @@ export class MetricsService {
|
|
|
209
218
|
static GetNvidiaGPUGrafanaDashboard(req: NvidiaGPUGrafanaDashboardRequest, initReq?: fm.InitReq): Promise<GrafanaDashboard> {
|
|
210
219
|
return fm.fetchReq<NvidiaGPUGrafanaDashboardRequest, GrafanaDashboard>(`/apis/baize.io/v1alpha1/grafana-dashboards/nvidia-gpu-overview?${fm.renderURLSearchParams(req, [])}`, {...initReq, method: "GET"})
|
|
211
220
|
}
|
|
221
|
+
static GetGPUGrafanaDashboard(req: GPUGrafanaDashboardRequest, initReq?: fm.InitReq): Promise<GrafanaDashboard> {
|
|
222
|
+
return fm.fetchReq<GPUGrafanaDashboardRequest, GrafanaDashboard>(`/apis/baize.io/v1alpha1/grafana-dashboards/gpu-overview?${fm.renderURLSearchParams(req, [])}`, {...initReq, method: "GET"})
|
|
223
|
+
}
|
|
212
224
|
}
|
|
@@ -83,6 +83,11 @@ export type ServingConfigVLLMLoraModel = {
|
|
|
83
83
|
relativePath?: string
|
|
84
84
|
}
|
|
85
85
|
|
|
86
|
+
export type ServingConfigVLLMCustomOptionalArg = {
|
|
87
|
+
argName?: string
|
|
88
|
+
argValues?: string[]
|
|
89
|
+
}
|
|
90
|
+
|
|
86
91
|
export type ServingConfigVLLM = {
|
|
87
92
|
trustRemoteCode?: boolean
|
|
88
93
|
tensorParallelSize?: number
|
|
@@ -91,6 +96,7 @@ export type ServingConfigVLLM = {
|
|
|
91
96
|
maxLorasRank?: number
|
|
92
97
|
maxLoras?: number
|
|
93
98
|
maxCpuLoras?: number
|
|
99
|
+
customOptionalArgs?: ServingConfigVLLMCustomOptionalArg[]
|
|
94
100
|
}
|
|
95
101
|
|
|
96
102
|
export type ServingConfigTritonModelConfig = {
|