@daocloud-proto/hydra 0.11.0-dev-38 → 0.11.0-dev-40
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.
|
@@ -30,6 +30,18 @@ export type InferenceRuntime = {
|
|
|
30
30
|
distributedSupported?: boolean
|
|
31
31
|
}
|
|
32
32
|
|
|
33
|
+
export type ListGPUTypesRequest = {
|
|
34
|
+
}
|
|
35
|
+
|
|
36
|
+
export type ListGPUTypesResponse = {
|
|
37
|
+
items?: GPUType[]
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
export type GPUType = {
|
|
41
|
+
gpuName?: string
|
|
42
|
+
gpuType?: string
|
|
43
|
+
}
|
|
44
|
+
|
|
33
45
|
export class Management {
|
|
34
46
|
static GetWebSearchAgentConfig(req: GetWebSearchAgentConfigRequest, initReq?: fm.InitReq): Promise<GetWebSearchAgentConfigResponse> {
|
|
35
47
|
return fm.fetchReq<GetWebSearchAgentConfigRequest, GetWebSearchAgentConfigResponse>(`/apis/hydra.io/v1alpha1/web-search-agent/config?${fm.renderURLSearchParams(req, [])}`, {...initReq, method: "GET"})
|
|
@@ -37,4 +49,7 @@ export class Management {
|
|
|
37
49
|
static ListInferenceRuntimes(req: ListInferenceRuntimesRequest, initReq?: fm.InitReq): Promise<ListInferenceRuntimesResponse> {
|
|
38
50
|
return fm.fetchReq<ListInferenceRuntimesRequest, ListInferenceRuntimesResponse>(`/apis/hydra.io/v1alpha1/inference-runtimes?${fm.renderURLSearchParams(req, [])}`, {...initReq, method: "GET"})
|
|
39
51
|
}
|
|
52
|
+
static ListGPUTypes(req: ListGPUTypesRequest, initReq?: fm.InitReq): Promise<ListGPUTypesResponse> {
|
|
53
|
+
return fm.fetchReq<ListGPUTypesRequest, ListGPUTypesResponse>(`/apis/hydra.io/v1alpha1/gpu-types?${fm.renderURLSearchParams(req, [])}`, {...initReq, method: "GET"})
|
|
54
|
+
}
|
|
40
55
|
}
|
|
@@ -30,14 +30,6 @@ export enum PublicModelConfigRateLimitLimitedBy {
|
|
|
30
30
|
API_KEY = "API_KEY",
|
|
31
31
|
}
|
|
32
32
|
|
|
33
|
-
export enum DeployTemplateGPUType {
|
|
34
|
-
GPU_TYPE_UNSPECIFIED = "GPU_TYPE_UNSPECIFIED",
|
|
35
|
-
NVIDIA_GPU = "NVIDIA_GPU",
|
|
36
|
-
NVIDIA_vGPU = "NVIDIA_vGPU",
|
|
37
|
-
NO_GPU = "NO_GPU",
|
|
38
|
-
METAX_GPU = "METAX_GPU",
|
|
39
|
-
}
|
|
40
|
-
|
|
41
33
|
export enum DeployTemplateInferenceRuntime {
|
|
42
34
|
INFERENCE_RUNTIME_UNSPECIFIED = "INFERENCE_RUNTIME_UNSPECIFIED",
|
|
43
35
|
VLLM = "VLLM",
|
|
@@ -103,7 +95,7 @@ export type ModelServingSpec = {
|
|
|
103
95
|
export type DeployTemplateResourcesRequirements = {
|
|
104
96
|
cpu?: number
|
|
105
97
|
memory?: number
|
|
106
|
-
gpuType?:
|
|
98
|
+
gpuType?: string
|
|
107
99
|
gpuCount?: number
|
|
108
100
|
perGpuMemory?: number
|
|
109
101
|
gpuCores?: number
|
|
@@ -64,7 +64,7 @@ export type WeightVolumeConfig = {
|
|
|
64
64
|
/* hydra modified */ export type BaseResourceConfig = {
|
|
65
65
|
cpu?: number
|
|
66
66
|
memory?: number
|
|
67
|
-
gpuType?:
|
|
67
|
+
gpuType?: string
|
|
68
68
|
gpuCount?: number
|
|
69
69
|
perGpuMemory?: number
|
|
70
70
|
}
|