diff --git a/GPU-Virtual-Service/README.md b/GPU-Virtual-Service/README.md index d299d01..71f5994 100644 --- a/GPU-Virtual-Service/README.md +++ b/GPU-Virtual-Service/README.md @@ -239,13 +239,13 @@ spec: - containerPort: 8000 resources: requests: # vgpu资源配置 - huawei.com/vgpu-number: 1 - huawei.com/vgpu-cores: 20 - huawei.com/vgpu-memory.1Gi: 3 + flexai.com/vgpu-number: 1 + flexai.com/vgpu-cores: 20 + flexai.com/vgpu-memory.1Gi: 3 limits: - huawei.com/vgpu-number: 1 - huawei.com/vgpu-cores: 20 - huawei.com/vgpu-memory.1Gi: 3 + flexai.com/vgpu-number: 1 + flexai.com/vgpu-cores: 20 + flexai.com/vgpu-memory.1Gi: 3 volumeMounts: - name: local-models mountPath: {path/to/DeepSeek-R1-Distill-llama-8B-main} # 填写模型权重路径 diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/client/client.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/client/client.go index df61bcf..377ad6a 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/client/client.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/client/client.go @@ -12,8 +12,8 @@ import ( "google.golang.org/grpc" - "huawei.com/vxpu-device-plugin/pkg/api/runtime/service" - "huawei.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/api/runtime/service" + "flexai.com/vxpu-device-plugin/pkg/log" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/cmd/main.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/cmd/main.go index 65f9168..fbb0e13 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/cmd/main.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/cmd/main.go @@ -13,12 +13,12 @@ import ( "github.com/fsnotify/fsnotify" "k8s.io/kubelet/pkg/apis/deviceplugin/v1beta1" - "huawei.com/vxpu-device-plugin/pkg/api/runtime/service" - "huawei.com/vxpu-device-plugin/pkg/log" - "huawei.com/vxpu-device-plugin/pkg/plugin" - "huawei.com/vxpu-device-plugin/pkg/plugin/config" - "huawei.com/vxpu-device-plugin/pkg/plugin/xpu" - "huawei.com/vxpu-device-plugin/watchers" + "flexai.com/vxpu-device-plugin/pkg/api/runtime/service" + "flexai.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/plugin" + "flexai.com/vxpu-device-plugin/pkg/plugin/config" + "flexai.com/vxpu-device-plugin/pkg/plugin/xpu" + "flexai.com/vxpu-device-plugin/watchers" ) const ( @@ -139,7 +139,7 @@ func main() { flag.StringVar(&config.NodeName, "node-name", os.Getenv("NODE_NAME"), "node name") // 日志目录：日志文件的存储目录 flag.StringVar(&config.LogDir, "log-dir", defaultLogDir, "log storage directory") - // 资源名称：Kubernetes 中的资源名称，用于向 kubelet 注册（如 "huawei.com/gpu"） + // 资源名称：Kubernetes 中的资源名称，用于向 kubelet 注册（如 "flexai.com/gpu"） flag.StringVar(&resourceName, "resource-name", xpu.VxpuNumber, "resource name") // GPU 类型配置文件：GPU 类型配置文件的绝对路径 flag.StringVar(&config.GPUTypeConfig, "gpu-type-config", "", "the abs path map of gpu type config file") diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-exceed.yml b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-exceed.yml index faf40c7..61c6735 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-exceed.yml +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-exceed.yml @@ -10,6 +10,6 @@ spec: command: ["bash", "-c", "sleep 86400"] resources: limits: - huawei.com/vgpu-number: 1 # requesting 1 vGPU - huawei.com/vgpu-memory.1Gi: 6 - # huawei.com/vgpu-cores: 80 \ No newline at end of file + flexai.com/vgpu-number: 1 # requesting 1 vGPU + flexai.com/vgpu-memory.1Gi: 6 + # flexai.com/vgpu-cores: 80 \ No newline at end of file diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-test.yml b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-test.yml index 47eb2c3..8d6ea0c 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-test.yml +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-test.yml @@ -10,9 +10,9 @@ spec: command: ["bash", "-c", "sleep 86400"] resources: limits: - huawei.com/vgpu-number: 1 # requesting 1 vGPU - huawei.com/vgpu-memory.1Gi:1 - huawei.com/vgpu-cores: 25 # percentage: 50 Each vGPU containers 50% device memory of that GPU. Can not be used with nvidia/gpumem + flexai.com/vgpu-number: 1 # requesting 1 vGPU + flexai.com/vgpu-memory.1Gi:1 + flexai.com/vgpu-cores: 25 # percentage: 50 Each vGPU containers 50% device memory of that GPU. Can not be used with nvidia/gpumem - name: ubuntu-container0 image: docker.io/nvidia/cuda:11.0.3-base-ubuntu18.04 command: ["bash", "-c", "sleep 86400"] @@ -21,5 +21,5 @@ spec: command: ["bash", "-c", "sleep 86400"] resources: limits: - huawei.com/vgpu-number: 1 # requesting 1 vGPU - huawei.com/vgpu-memory.1Gi:1 \ No newline at end of file + flexai.com/vgpu-number: 1 # requesting 1 vGPU + flexai.com/vgpu-memory.1Gi:1 \ No newline at end of file diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-whole-card.yml b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-whole-card.yml index c5745e8..36d9233 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-whole-card.yml +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/examples/vgpu-whole-card.yml @@ -10,4 +10,4 @@ spec: command: ["bash", "-c", "sleep 86400"] resources: limits: - huawei.com/vgpu-number: 1 # requesting 1 vGPU \ No newline at end of file + flexai.com/vgpu-number: 1 # requesting 1 vGPU \ No newline at end of file diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/go.mod b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/go.mod index a463f15..8e5bd74 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/go.mod +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/go.mod @@ -1,4 +1,4 @@ -module huawei.com/vxpu-device-plugin +module flexai.com/vxpu-device-plugin go 1.22.1 diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/api/runtime/service/service_impl.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/api/runtime/service/service_impl.go index 51497f5..c2135a0 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/api/runtime/service/service_impl.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/api/runtime/service/service_impl.go @@ -17,11 +17,11 @@ import ( "time" "google.golang.org/grpc" - "huawei.com/vxpu-device-plugin/pkg/log" - "huawei.com/vxpu-device-plugin/pkg/plugin/config" - "huawei.com/vxpu-device-plugin/pkg/plugin/types" - "huawei.com/vxpu-device-plugin/pkg/plugin/util" - "huawei.com/vxpu-device-plugin/pkg/plugin/xpu" + "flexai.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/plugin/config" + "flexai.com/vxpu-device-plugin/pkg/plugin/types" + "flexai.com/vxpu-device-plugin/pkg/plugin/util" + "flexai.com/vxpu-device-plugin/pkg/plugin/xpu" "k8s.io/api/core/v1" metav1 "k8s.io/apimachinery/pkg/apis/meta/v1" "k8s.io/apimachinery/pkg/fields" diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/lock/nodelock.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/lock/nodelock.go index a91d40d..091745b 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/lock/nodelock.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/lock/nodelock.go @@ -10,7 +10,7 @@ import ( "strings" "time" - "huawei.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/log" "k8s.io/apimachinery/pkg/apis/meta/v1" "k8s.io/client-go/kubernetes" "k8s.io/client-go/rest" diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/cache.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/cache.go index d487b22..e3516c1 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/cache.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/cache.go @@ -6,7 +6,7 @@ import ( "k8s.io/kubelet/pkg/apis/deviceplugin/v1beta1" - "huawei.com/vxpu-device-plugin/pkg/plugin/xpu" + "flexai.com/vxpu-device-plugin/pkg/plugin/xpu" ) // DeviceCache provide xpu device cache for plugin and register diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/plugin.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/plugin.go index 1ab9a2b..8dbf8d8 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/plugin.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/plugin.go @@ -15,12 +15,12 @@ import ( "google.golang.org/grpc" "k8s.io/kubelet/pkg/apis/deviceplugin/v1beta1" - "huawei.com/vxpu-device-plugin/pkg/lock" - "huawei.com/vxpu-device-plugin/pkg/log" - "huawei.com/vxpu-device-plugin/pkg/plugin/config" - "huawei.com/vxpu-device-plugin/pkg/plugin/types" - "huawei.com/vxpu-device-plugin/pkg/plugin/util" - "huawei.com/vxpu-device-plugin/pkg/plugin/xpu" + "flexai.com/vxpu-device-plugin/pkg/lock" + "flexai.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/plugin/config" + "flexai.com/vxpu-device-plugin/pkg/plugin/types" + "flexai.com/vxpu-device-plugin/pkg/plugin/util" + "flexai.com/vxpu-device-plugin/pkg/plugin/xpu" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/register.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/register.go index 7fa0407..ca05735 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/register.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/register.go @@ -9,12 +9,12 @@ import ( "gopkg.in/yaml.v2" - "huawei.com/vxpu-device-plugin/pkg/graph" - "huawei.com/vxpu-device-plugin/pkg/log" - "huawei.com/vxpu-device-plugin/pkg/plugin/config" - "huawei.com/vxpu-device-plugin/pkg/plugin/types" - "huawei.com/vxpu-device-plugin/pkg/plugin/util" - "huawei.com/vxpu-device-plugin/pkg/plugin/xpu" + "flexai.com/vxpu-device-plugin/pkg/graph" + "flexai.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/plugin/config" + "flexai.com/vxpu-device-plugin/pkg/plugin/types" + "flexai.com/vxpu-device-plugin/pkg/plugin/util" + "flexai.com/vxpu-device-plugin/pkg/plugin/xpu" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/types/types.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/types/types.go index 482a2c1..4f67e29 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/types/types.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/types/types.go @@ -3,9 +3,9 @@ package types const ( // DeviceBindTime allocate bind time - DeviceBindTime = "huawei.com/bind-time" + DeviceBindTime = "flexai.com/bind-time" // DeviceBindPhase allocate bind phase - DeviceBindPhase = "huawei.com/bind-phase" + DeviceBindPhase = "flexai.com/bind-phase" // DeviceBindAllocating bind phase allocating DeviceBindAllocating = "allocating" diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/util/util.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/util/util.go index f057113..6a68a12 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/util/util.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/util/util.go @@ -16,11 +16,11 @@ import ( "k8s.io/apimachinery/pkg/fields" k8stypes "k8s.io/apimachinery/pkg/types" - "huawei.com/vxpu-device-plugin/pkg/lock" - "huawei.com/vxpu-device-plugin/pkg/log" - "huawei.com/vxpu-device-plugin/pkg/plugin/config" - "huawei.com/vxpu-device-plugin/pkg/plugin/types" - "huawei.com/vxpu-device-plugin/pkg/plugin/xpu" + "flexai.com/vxpu-device-plugin/pkg/lock" + "flexai.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/plugin/config" + "flexai.com/vxpu-device-plugin/pkg/plugin/types" + "flexai.com/vxpu-device-plugin/pkg/plugin/xpu" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/xpu/gpu.go b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/xpu/gpu.go index 9c8c0a2..e3179d5 100644 --- a/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/xpu/gpu.go +++ b/GPU-Virtual-Service/xpu-pool-service/GPU-device-plugin/pkg/plugin/xpu/gpu.go @@ -17,20 +17,20 @@ import ( "k8s.io/kubelet/pkg/apis/deviceplugin/v1beta1" - "huawei.com/vxpu-device-plugin/pkg/gonvml" - "huawei.com/vxpu-device-plugin/pkg/graph" - "huawei.com/vxpu-device-plugin/pkg/log" - "huawei.com/vxpu-device-plugin/pkg/plugin/config" - "huawei.com/vxpu-device-plugin/pkg/plugin/types" + "flexai.com/vxpu-device-plugin/pkg/gonvml" + "flexai.com/vxpu-device-plugin/pkg/graph" + "flexai.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/plugin/config" + "flexai.com/vxpu-device-plugin/pkg/plugin/types" ) const ( // VxpuNumber vxpu number resource name - VxpuNumber = "huawei.com/vgpu-number" + VxpuNumber = "flexai.com/vgpu-number" // VxpuCore vxpu core resource name - VxpuCore = "huawei.com/vgpu-cores" + VxpuCore = "flexai.com/vgpu-cores" // VxpuMemory vxpu memory resource name - VxpuMemory = "huawei.com/vgpu-memory.1Gi" + VxpuMemory = "flexai.com/vgpu-memory.1Gi" microSecond = 1000 * 1000 milliwatts = 1000 eventWaitTimeout = 5000 @@ -45,15 +45,15 @@ const ( VxpuIdsConfigFileName = "vgpu-ids.config" // DeviceAssign device type supported by the device plugin DeviceType = "GPU" - AssignedIDs = "huawei.com/vgpu-ids-new" - AssignedIDsToAllocate = "huawei.com/vgpu-devices-to-allocate" - NodeVXPUHandshake = "huawei.com/node-vgpu-handshake" - NodeVXPURegister = "huawei.com/node-vgpu-register" - NodeVXPUUsed = "huawei.com/node-vgpu-used" + AssignedIDs = "flexai.com/vgpu-ids-new" + AssignedIDsToAllocate = "flexai.com/vgpu-devices-to-allocate" + NodeVXPUHandshake = "flexai.com/node-vgpu-handshake" + NodeVXPURegister = "flexai.com/node-vgpu-register" + NodeVXPUUsed = "flexai.com/node-vgpu-used" // AssignedNode assigned node name - AssignedNode = "huawei.com/vgpu-node" + AssignedNode = "flexai.com/vgpu-node" // NodeXpuTopology node gpu topology - NodeXpuTopology = "huawei.com/node-gpu-topology" + NodeXpuTopology = "flexai.com/node-gpu-topology" ) var ( diff --git a/GPU-Virtual-Service/xpu-pool-service/install/gpu_env_init.sh b/GPU-Virtual-Service/xpu-pool-service/install/gpu_env_init.sh index 9d1d3ea..dc01c73 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/gpu_env_init.sh +++ b/GPU-Virtual-Service/xpu-pool-service/install/gpu_env_init.sh @@ -1,5 +1,6 @@ #!/bin/bash -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. set -e @@ -27,4 +28,4 @@ else exit 1 fi -kubectl label node ${host_name} huawei.com/vgpu=ready \ No newline at end of file +kubectl label node ${host_name} flexai.com/vgpu=ready \ No newline at end of file diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/Chart.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/Chart.yaml index cba7a73..4020560 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/Chart.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/Chart.yaml @@ -1,4 +1,5 @@ -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: v2 name: gpupool diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/NOTES.txt b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/NOTES.txt index 7e78df2..a08b979 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/NOTES.txt +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/NOTES.txt @@ -1,3 +1,4 @@ -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. Thank you for installing {{ .Chart.Name }}. diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-client-update-daemonset.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-client-update-daemonset.yaml index a6f7f58..67b77d8 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-client-update-daemonset.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-client-update-daemonset.yaml @@ -1,4 +1,5 @@ -# Copyright Huawei Technologies Co., Ltd. 2024-2025. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: apps/v1 kind: DaemonSet metadata: diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-device-plugin-configmap.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-device-plugin-configmap.yaml index 65b9a42..5a7cdfb 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-device-plugin-configmap.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-device-plugin-configmap.yaml @@ -1,4 +1,5 @@ -# Copyright Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: v1 kind: ConfigMap metadata: @@ -6,7 +7,8 @@ metadata: namespace: {{ .Values.basic.namespace }} data: gpu-type.conf: | - # Copyright Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. + # Copyright (c) 2025 Shanghai Jiao Tong University. + # Contributed to the ModelEngine Community. {{ range $key, $value := .Values.gpuTypeMap }} {{ $key }}: {{ $value }} {{ end }} \ No newline at end of file diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-device-plugin-daemonset.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-device-plugin-daemonset.yaml index 1a8144b..7a7ae35 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-device-plugin-daemonset.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/gpu-device-plugin-daemonset.yaml @@ -1,4 +1,5 @@ -# Copyright Huawei Technologies Co., Ltd. 2024-2025. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: apps/v1 kind: DaemonSet metadata: diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/role-binding.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/role-binding.yaml index 2e6c177..627a171 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/role-binding.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/role-binding.yaml @@ -1,4 +1,5 @@ -# Copyright Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/role.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/role.yaml index 20de5a8..5ea4663 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/role.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/role.yaml @@ -1,4 +1,5 @@ -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/service-account.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/service-account.yaml index 49490d1..eee1936 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/service-account.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/service-account.yaml @@ -1,4 +1,5 @@ -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: v1 kind: ServiceAccount diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-exporter-daemonset.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-exporter-daemonset.yaml index 435132f..fb87026 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-exporter-daemonset.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-exporter-daemonset.yaml @@ -1,4 +1,5 @@ -# Copyright Huawei Technologies Co., Ltd. 2024-2025. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: apps/v1 kind: DaemonSet metadata: diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-exporter-service.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-exporter-service.yaml index c2660ba..57b7c7c 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-exporter-service.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-exporter-service.yaml @@ -1,4 +1,5 @@ -# Copyright Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: v1 kind: Service metadata: diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-servicemonitor.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-servicemonitor.yaml index d17d25f..da0d58f 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-servicemonitor.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/templates/xpu-servicemonitor.yaml @@ -1,4 +1,5 @@ -# Copyright Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. {{- if .Values.ServiceMonitor.enable }} apiVersion: monitoring.coreos.com/v1 kind: ServiceMonitor diff --git a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/values.yaml b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/values.yaml index f695bd9..154317b 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/values.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/helm/gpupool/values.yaml @@ -1,4 +1,5 @@ -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. basic: swr_addr: "docker.io/library" @@ -6,10 +7,10 @@ basic: gpu: nodeSelector: - huawei.com/vgpu: ready + flexai.com/vgpu: ready npu: nodeSelector: - huawei.com/vnpu: ready + flexai.com/vnpu: ready gpuDevicePlugin: name: gpu-device-plugin diff --git a/GPU-Virtual-Service/xpu-pool-service/install/install.sh b/GPU-Virtual-Service/xpu-pool-service/install/install.sh index 72e83ac..aa845d9 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/install.sh +++ b/GPU-Virtual-Service/xpu-pool-service/install/install.sh @@ -1,5 +1,6 @@ #!/bin/bash -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. set -e diff --git a/GPU-Virtual-Service/xpu-pool-service/install/npu_env_init.sh b/GPU-Virtual-Service/xpu-pool-service/install/npu_env_init.sh index 140c022..ba3ec5c 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/npu_env_init.sh +++ b/GPU-Virtual-Service/xpu-pool-service/install/npu_env_init.sh @@ -1,7 +1,8 @@ #!/bin/bash -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. set -e host_name=$(hostname) -kubectl label node ${host_name} huawei.com/vnpu=ready \ No newline at end of file +kubectl label node ${host_name} flexai.com/vnpu=ready \ No newline at end of file diff --git a/GPU-Virtual-Service/xpu-pool-service/install/uninstall.sh b/GPU-Virtual-Service/xpu-pool-service/install/uninstall.sh index b7fd0e1..aedc5b6 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/uninstall.sh +++ b/GPU-Virtual-Service/xpu-pool-service/install/uninstall.sh @@ -1,5 +1,6 @@ #!/bin/bash -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. set -e diff --git a/GPU-Virtual-Service/xpu-pool-service/install/yaml/client-update.yaml b/GPU-Virtual-Service/xpu-pool-service/install/yaml/client-update.yaml index fdbb43f..157b0ca 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/yaml/client-update.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/yaml/client-update.yaml @@ -1,4 +1,5 @@ -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: apps/v1 kind: DaemonSet @@ -17,7 +18,7 @@ spec: name: client-update spec: nodeSelector: - huawei.com/vgpu: ready + flexai.com/vgpu: ready priorityClassName: "system-node-critical" hostPID: true hostNetwork: true diff --git a/GPU-Virtual-Service/xpu-pool-service/install/yaml/gpu-device-plugin.yaml b/GPU-Virtual-Service/xpu-pool-service/install/yaml/gpu-device-plugin.yaml index 7fb3db5..de437cc 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/yaml/gpu-device-plugin.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/yaml/gpu-device-plugin.yaml @@ -1,4 +1,5 @@ -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole @@ -77,7 +78,7 @@ spec: name: gpu-device-plugin spec: nodeSelector: - huawei.com/vgpu: ready + flexai.com/vgpu: ready # Mark this pod as a critical add-on; when enabled, the critical add-on # scheduler reserves resources for critical add-on pods so that they can be scheduled after a failure. # See https://kubernetes.io/docs/tasks/administer-cluster/guraranteed-scheduling-critical-addon-pods/ diff --git a/GPU-Virtual-Service/xpu-pool-service/install/yaml/namespace.yaml b/GPU-Virtual-Service/xpu-pool-service/install/yaml/namespace.yaml index 4a7cad6..d061152 100644 --- a/GPU-Virtual-Service/xpu-pool-service/install/yaml/namespace.yaml +++ b/GPU-Virtual-Service/xpu-pool-service/install/yaml/namespace.yaml @@ -1,4 +1,5 @@ -# Copyright (C) Huawei Technologies Co., Ltd. 2024-2024. All rights reserved. +# Copyright (c) 2025 Shanghai Jiao Tong University. +# Contributed to the ModelEngine Community. apiVersion: v1 kind: Namespace diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/Makefile b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/Makefile index 856d2d9..28452f9 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/Makefile +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/Makefile @@ -17,8 +17,8 @@ xpu-exporter: go build \ -buildmode=pie \ -ldflags="-s -w -linkmode 'external' -extldflags '$(EXTLDFLAGS)' \ - -X huawei.com/npu-exporter/v6/versions.BuildName=${OUTPUT_NAME} \ - -X huawei.com/xpu-exporter/versions.BuildVersion=${build_version}" \ + -X flexai.com/npu-exporter/v6/versions.BuildName=${OUTPUT_NAME} \ + -X flexai.com/xpu-exporter/versions.BuildVersion=${build_version}" \ -o xpu-exporter \ ./cmd/xpu-exporter diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/cmd/xpu-exporter/main.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/cmd/xpu-exporter/main.go index bb11898..84bc2ce 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/cmd/xpu-exporter/main.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/cmd/xpu-exporter/main.go @@ -14,11 +14,11 @@ import ( "time" "github.com/prometheus/client_golang/prometheus" - "huawei.com/vxpu-device-plugin/pkg/log" - "huawei.com/xpu-exporter/collector/gpuservice" - "huawei.com/xpu-exporter/collector/npuservice" - "huawei.com/xpu-exporter/server" - "huawei.com/xpu-exporter/versions" + "flexai.com/vxpu-device-plugin/pkg/log" + "flexai.com/xpu-exporter/collector/gpuservice" + "flexai.com/xpu-exporter/collector/npuservice" + "flexai.com/xpu-exporter/server" + "flexai.com/xpu-exporter/versions" ) var ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/gpuservice/gpu_collector.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/gpuservice/gpu_collector.go index 580cde4..88af6e7 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/gpuservice/gpu_collector.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/gpuservice/gpu_collector.go @@ -9,12 +9,12 @@ import ( "time" "github.com/prometheus/client_golang/prometheus" - "huawei.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/log" - "huawei.com/xpu-exporter/common/cache" - "huawei.com/xpu-exporter/common/client" - "huawei.com/xpu-exporter/common/utils" - "huawei.com/xpu-exporter/versions" + "flexai.com/xpu-exporter/common/cache" + "flexai.com/xpu-exporter/common/client" + "flexai.com/xpu-exporter/common/utils" + "flexai.com/xpu-exporter/versions" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/gpuservice/gpu_collector_service.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/gpuservice/gpu_collector_service.go index cd07a00..566fad6 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/gpuservice/gpu_collector_service.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/gpuservice/gpu_collector_service.go @@ -7,9 +7,9 @@ import ( "time" "github.com/prometheus/client_golang/prometheus" - "huawei.com/xpu-exporter/collector" - "huawei.com/xpu-exporter/common/cache" - "huawei.com/xpu-exporter/common/client" + "flexai.com/xpu-exporter/collector" + "flexai.com/xpu-exporter/common/cache" + "flexai.com/xpu-exporter/common/client" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/npuservice/npu_collector.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/npuservice/npu_collector.go index 56df918..e34d44d 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/npuservice/npu_collector.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/npuservice/npu_collector.go @@ -6,8 +6,8 @@ import ( "github.com/prometheus/client_golang/prometheus" - "huawei.com/xpu-exporter/common/cache" - "huawei.com/xpu-exporter/versions" + "flexai.com/xpu-exporter/common/cache" + "flexai.com/xpu-exporter/versions" ) var ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/npuservice/npu_collector_service.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/npuservice/npu_collector_service.go index ac02132..650f01e 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/npuservice/npu_collector_service.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/collector/npuservice/npu_collector_service.go @@ -7,8 +7,8 @@ import ( "github.com/prometheus/client_golang/prometheus" - "huawei.com/xpu-exporter/collector" - "huawei.com/xpu-exporter/common/cache" + "flexai.com/xpu-exporter/collector" + "flexai.com/xpu-exporter/common/cache" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/cache/lrucache_test.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/cache/lrucache_test.go index 9f4df87..0a5549a 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/cache/lrucache_test.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/cache/lrucache_test.go @@ -5,7 +5,7 @@ import ( "testing" "time" - "huawei.com/xpu-exporter/common" + "flexai.com/xpu-exporter/common" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/client/client.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/client/client.go index 3b1a447..97a35cb 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/client/client.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/client/client.go @@ -7,7 +7,7 @@ import ( "time" "google.golang.org/grpc" - "huawei.com/xpu-exporter/common/service" + "flexai.com/xpu-exporter/common/service" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/client/client_test.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/client/client_test.go index d3f5441..69793e9 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/client/client_test.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/client/client_test.go @@ -8,7 +8,7 @@ import ( "github.com/agiledragon/gomonkey/v2" "google.golang.org/grpc" - "huawei.com/xpu-exporter/common/service" + "flexai.com/xpu-exporter/common/service" ) type mockClient struct { diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_handler.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_handler.go index 3dc4998..ea473ef 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_handler.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_handler.go @@ -14,8 +14,8 @@ import ( "syscall" "time" - "huawei.com/xpu-exporter/common/cache" - "huawei.com/xpu-exporter/common/utils" + "flexai.com/xpu-exporter/common/cache" + "flexai.com/xpu-exporter/common/utils" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_handler_test.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_handler_test.go index c7efdf1..403ea4a 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_handler_test.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_handler_test.go @@ -9,7 +9,7 @@ import ( "time" "github.com/agiledragon/gomonkey/v2" - "huawei.com/xpu-exporter/common" + "flexai.com/xpu-exporter/common" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_listener.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_listener.go index b42ed22..db8f555 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_listener.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/common/limiter/limit_listener.go @@ -8,7 +8,7 @@ import ( "sync" "time" - "huawei.com/xpu-exporter/common/cache" + "flexai.com/xpu-exporter/common/cache" ) const ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/go.mod b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/go.mod index 52722ed..2be1c4a 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/go.mod +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/go.mod @@ -1,10 +1,10 @@ -module huawei.com/xpu-exporter +module flexai.com/xpu-exporter go 1.22.1 replace ( google.golang.org/grpc => google.golang.org/grpc v1.57.2 - huawei.com/vxpu-device-plugin => ../GPU-device-plugin + flexai.com/vxpu-device-plugin => ../GPU-device-plugin ) require ( @@ -13,7 +13,7 @@ require ( github.com/stretchr/testify v1.9.0 google.golang.org/grpc v1.65.0 google.golang.org/protobuf v1.34.2 - huawei.com/vxpu-device-plugin v0.0.0-00010101000000-000000000000 + flexai.com/vxpu-device-plugin v0.0.0-00010101000000-000000000000 ) require ( diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/server/prometheus.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/server/prometheus.go index 05bc176..07f56e4 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/server/prometheus.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/server/prometheus.go @@ -18,8 +18,8 @@ import ( "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/promhttp" - "huawei.com/xpu-exporter/collector" - "huawei.com/xpu-exporter/common/limiter" + "flexai.com/xpu-exporter/collector" + "flexai.com/xpu-exporter/common/limiter" ) type ProtocolType int diff --git a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/server/prometheus_test.go b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/server/prometheus_test.go index 8c1205b..7182e63 100644 --- a/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/server/prometheus_test.go +++ b/GPU-Virtual-Service/xpu-pool-service/xpu-exporter/server/prometheus_test.go @@ -13,7 +13,7 @@ import ( "github.com/agiledragon/gomonkey/v2" "github.com/prometheus/client_golang/prometheus" "github.com/stretchr/testify/assert" - "huawei.com/vxpu-device-plugin/pkg/log" + "flexai.com/vxpu-device-plugin/pkg/log" ) type mockCollectorService struct{} diff --git a/LICENSE b/LICENSE index ee54858..5fd2512 100644 --- a/LICENSE +++ b/LICENSE @@ -1,6 +1,7 @@ The MIT License -Copyright (c) 2025 Huawei Technologies Co., Ltd. All rights reserved. +Copyright (c) 2025 Shanghai Jiao Tong University. +Contributed to the ModelEngine Community. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal