Kill python3 xpk.py (#812)

feat: kill python3 xpk.py

Author: scaliby

README.md

@@ -61,7 +61,7 @@ Also, follow [Prerequisites](https://github.com/AI-Hypercomputer/xpk?tab=readme-
 
 ### Make your change
 
-Make intended code change, cover it with unit tests and iterate on the code by executing local XPK version via `python3 xpk.py`.
+Make intended code change, cover it with unit tests and iterate on the code by executing local XPK version via `xpk`.
 
 ### Verify change against checklist
 

docs/contributing.md

@@ -8,7 +8,7 @@ This section should describe how to prepare volumes and add external files execu
 
 To run xpk batch script run:
 ```bash
-python3 xpk.py batch --cluster my-cluster job.sh
+xpk batch --cluster my-cluster job.sh
 ```
 
 To view results run:

examples/batch.md

@@ -11,7 +11,7 @@ Skip this step if you have already provisioned a GKE cluster with A3 Ultra or A3
 First step is to create a cluster with A3 Ultra or A3 Mega machine. Execute command below:
 
 ```
-python3 xpk.py cluster create \
+xpk cluster create \
     --cluster=$CLUSTER_NAME --device-type=$DEVICE_TYPE \
     --zone=$COMPUTE_ZONE  --project=$PROJECT_ID \
     --num-nodes=$CLUSTER_NUM_NODES --reservation=$RESERVATION_ID
@@ -26,7 +26,7 @@ The command to run NCCL tests on A3 clusters depends on the type of machine.
 
 
 ```bash
-python3 xpk.py workload create \
+xpk workload create \
     --workload=nccl-test --command="./examples/nccl/nccl-a3mega.sh" \
     --base-docker-image=us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpxo/nccl-plugin-gpudirecttcpx-dev:v1.0.8-1 \
     --cluster=$CLUSTER_NAME --device-type=$DEVICE_TYPE \
@@ -37,7 +37,7 @@ python3 xpk.py workload create \
 #### A3 Ultra
 
 ```bash
-python3 xpk.py workload create \
+xpk workload create \
     --workload=nccl-test --command="./examples/nccl/nccl-a3ultra.sh" \
     --base-docker-image=us-docker.pkg.dev/gce-ai-infra/gpudirect-gib/nccl-plugin-gib-diagnostic:v1.0.3 \
     --cluster=$CLUSTER_NAME --device-type=$DEVICE_TYPE \

examples/nccl/nccl.md

@@ -1,37 +1,37 @@
 goldens:
   "NAP cluster-create with pathways":
-    command: python3 xpk.py cluster create-pathways --project=golden-project --zone=us-central1-a --enable-autoprovisioning --cluster=golden-cluster --tpu-type=tpu7x-8 --on-demand --dry-run
+    command: xpk cluster create-pathways --project=golden-project --zone=us-central1-a --enable-autoprovisioning --cluster=golden-cluster --tpu-type=tpu7x-8 --on-demand --dry-run
   "NAP cluster-create":
-    command: python3 xpk.py cluster create --project=golden-project --zone=us-central1-a --enable-autoprovisioning --cluster=golden-cluster --tpu-type=tpu7x-8 --on-demand --dry-run
+    command: xpk cluster create --project=golden-project --zone=us-central1-a --enable-autoprovisioning --cluster=golden-cluster --tpu-type=tpu7x-8 --on-demand --dry-run
   "Basic cluster create":
-    command: python3 xpk.py cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --dry-run
+    command: xpk cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --dry-run
   "Cluster create with CPU and memory limits below capacity":
-    command: python3 xpk.py cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --cpu-limit=1 --memory-limit=1Mi --dry-run
+    command: xpk cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --cpu-limit=1 --memory-limit=1Mi --dry-run
   "Cluster create with CPU and memory limits above capacity":
-    command: python3 xpk.py cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --cpu-limit=20 --memory-limit=1Gi --dry-run
+    command: xpk cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --cpu-limit=20 --memory-limit=1Gi --dry-run
   "Cluster create with gb200-4":
-    command: python3 xpk.py cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --device-type=gb200-4 --reservation=golden-reservation --dry-run
+    command: xpk cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --device-type=gb200-4 --reservation=golden-reservation --dry-run
   "Cluster create private":
-    command: python3 xpk.py cluster create-pathways --project=golden-project --zone=us-central1-a --cluster=golden-cluster-private --private --tpu-type=v5p-8  --num-slices=1 --default-pool-cpu-machine-type=n1-standard-16 --default-pool-cpu-num-nodes=4 --reservation=golden-reservation --dry-run
+    command: xpk cluster create-pathways --project=golden-project --zone=us-central1-a --cluster=golden-cluster-private --private --tpu-type=v5p-8  --num-slices=1 --default-pool-cpu-machine-type=n1-standard-16 --default-pool-cpu-num-nodes=4 --reservation=golden-reservation --dry-run
   "Cluster delete":
-    command: python3 xpk.py cluster delete --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
+    command: xpk cluster delete --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
   "Cluster delete force":
-    command: python3 xpk.py cluster delete --project=golden-project --zone=us-central1-a --cluster=golden-cluster --force --dry-run
+    command: xpk cluster delete --project=golden-project --zone=us-central1-a --cluster=golden-cluster --force --dry-run
   "Workload create":
-    command: python3 xpk.py workload create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --workload=golden-workload --command "bash hello" --tpu-type=v5p-8 --num-slices=1 --script-dir=/tmp --dry-run
+    command: xpk workload create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --workload=golden-workload --command "bash hello" --tpu-type=v5p-8 --num-slices=1 --script-dir=/tmp --dry-run
   "Workload create pathways":
-    command: python3 xpk.py workload create-pathways --project=golden-project --zone=us-central1-a --cluster=golden-cluster --workload=golden-workload --command "bash hello" --tpu-type=v5p-8 --num-slices=1 --script-dir=/tmp --dry-run
+    command: xpk workload create-pathways --project=golden-project --zone=us-central1-a --cluster=golden-cluster --workload=golden-workload --command "bash hello" --tpu-type=v5p-8 --num-slices=1 --script-dir=/tmp --dry-run
   "Workload delete":
-    command: python3 xpk.py workload delete --project=golden-project --zone=us-central1-a --cluster=golden-cluster --workload=golden-workload --dry-run
+    command: xpk workload delete --project=golden-project --zone=us-central1-a --cluster=golden-cluster --workload=golden-workload --dry-run
   "Workload list":
-    command: python3 xpk.py workload list --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
+    command: xpk workload list --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
   "Storage list":
-    command: python3 xpk.py storage list --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
+    command: xpk storage list --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
   "Job cancel":
-    command: python3 xpk.py job cancel golden-job --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
+    command: xpk job cancel golden-job --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
   "Batch":
-    command: python3 xpk.py batch --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run batch-read.sh
+    command: xpk batch --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run batch-read.sh
   "Job list":
-    command: python3 xpk.py job ls --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
+    command: xpk job ls --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
   "Job info":
-    command: python3 xpk.py job info golden-job --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run
+    command: xpk job info golden-job --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run

goldens.yaml

@@ -1,4 +1,4 @@
-$ python3 xpk.py cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --dry-run
+$ xpk cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --dry-run
 [XPK] Starting xpk v0.14.3
 [XPK] Starting cluster create for cluster golden-cluster:
 [XPK] Working on golden-project and us-central1-a

goldens/Basic_cluster_create.txt

@@ -1,4 +1,4 @@
-$ python3 xpk.py batch --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run batch-read.sh
+$ xpk batch --project=golden-project --zone=us-central1-a --cluster=golden-cluster --dry-run batch-read.sh
 [XPK] Starting xpk v0.14.3
 [XPK] Working on golden-project and us-central1-a
 [XPK] Task: `Find cluster region or zone` is implemented by the following command not running since it is a dry run. 

goldens/Batch.txt

@@ -1,4 +1,4 @@
-$ python3 xpk.py cluster create-pathways --project=golden-project --zone=us-central1-a --cluster=golden-cluster-private --private --tpu-type=v5p-8  --num-slices=1 --default-pool-cpu-machine-type=n1-standard-16 --default-pool-cpu-num-nodes=4 --reservation=golden-reservation --dry-run
+$ xpk cluster create-pathways --project=golden-project --zone=us-central1-a --cluster=golden-cluster-private --private --tpu-type=v5p-8  --num-slices=1 --default-pool-cpu-machine-type=n1-standard-16 --default-pool-cpu-num-nodes=4 --reservation=golden-reservation --dry-run
 [XPK] Starting xpk v0.14.3
 [XPK] Starting cluster create for cluster golden-cluster-private:
 [XPK] Working on golden-project and us-central1-a

goldens/Cluster_create_private.txt

@@ -1,4 +1,4 @@
-$ python3 xpk.py cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --cpu-limit=20 --memory-limit=1Gi --dry-run
+$ xpk cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --cpu-limit=20 --memory-limit=1Gi --dry-run
 [XPK] Starting xpk v0.14.3
 [XPK] Starting cluster create for cluster golden-cluster:
 [XPK] Working on golden-project and us-central1-a

goldens/Cluster_create_with_CPU_and_memory_limits_above_capacity.txt

@@ -1,4 +1,4 @@
-$ python3 xpk.py cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --cpu-limit=1 --memory-limit=1Mi --dry-run
+$ xpk cluster create --project=golden-project --zone=us-central1-a --cluster=golden-cluster --tpu-type=tpu7x-8 --spot --cpu-limit=1 --memory-limit=1Mi --dry-run
 [XPK] Starting xpk v0.14.3
 [XPK] Starting cluster create for cluster golden-cluster:
 [XPK] Working on golden-project and us-central1-a