feat(infra): add support for autogenerate CI runners

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

.github/workflows/ci.yml

@@ -26,15 +26,17 @@ jobs:
       - name: setup tooling
         run: |
           python -m pip install uv
-          uv pip install --system httpx
+          uv pip install --system httpx orjson
       - name: startup machine
-        run: python tools/machines.py --start ${{ secrets.PAPERSPACE_MACHINE_ID }} || true
+        id: paperspace-machine
+        run: |
+          echo "$(python tools/machines.py --ci-template ${{secrets.PAPERSPACE_TEMPLATE_ID}})" >> $GITHUB_OUTPUT
       - name: running regression tests (PR)
         uses: appleboy/ssh-action@029f5b4aeeeb58fdfe1410a5d17f967dacf36262 # ratchet:appleboy/ssh-action@v1.0.3
         if: github.event_name == 'pull_request'
         with:
-          host: ${{secrets.PAPERSPACE_HOST}}
-          username: ${{secrets.PAPERSPACE_USERNAME}}
+          host: ${{steps.outputs.paperspace-machine.outputs.publicIp}}
+          username: paperspace
           key: ${{secrets.PAPERSPACE_SSH_KEY}}
           port: ${{secrets.PAPERSPACE_PORT}}
           script: /nix/var/nix/profiles/default/bin/nix run github:aarnphm/dix#openllm-ci --refresh -- --pr ${{github.event.number}}
@@ -42,11 +44,13 @@ jobs:
         uses: appleboy/ssh-action@029f5b4aeeeb58fdfe1410a5d17f967dacf36262 # ratchet:appleboy/ssh-action@v1.0.3
         if: ${{ !github.event.repository.fork && github.event_name == 'push' }}
         with:
-          host: ${{secrets.PAPERSPACE_HOST}}
-          username: ${{secrets.PAPERSPACE_USERNAME}}
+          host: ${{steps.outputs.paperspace-machine.outputs.ip}}
+          username: paperspace
           key: ${{secrets.PAPERSPACE_SSH_KEY}}
           port: ${{secrets.PAPERSPACE_PORT}}
           script: /nix/var/nix/profiles/default/bin/nix run github:aarnphm/dix#openllm-ci --refresh -- --head
+      - name: shutdown machine
+        run: python tools/machines.py --delete ${{ steps.outputs.paperspace-machine.outputs.ip }}
   evergreen: # https://github.com/marketplace/actions/alls-green#why
     if: always()
     needs:

tools/machines.py

@@ -1,19 +1,15 @@
 from __future__ import annotations
 
-import httpx,os,dataclasses,logging,time,argparse,typing as t
+import httpx,os,dataclasses,datetime,time,argparse,typing as t
 
 if (ENV := os.getenv("PAPERSPACE_API_KEY")) is None: raise RuntimeError('This script requires setting "PAPERSPACE_API_KEY"')
 HEADERS = httpx.Headers({'Authorization': f'Bearer {ENV}', 'Accept': 'application/json'})
 API_URL = 'https://api.paperspace.com/v1'
 
-logging.basicConfig(level=logging.ERROR)
-logger = logging.getLogger(__name__)
-
 @dataclasses.dataclass
 class Machine:
   id: str
   inner: httpx.Client = dataclasses.field(default_factory=lambda: httpx.Client(headers=HEADERS, base_url=API_URL, timeout=60), repr=False)
-
   def close(self): self.inner.close()
   def __del__(self): self.close()
   def __enter__(self): return self
@@ -25,44 +21,70 @@ class Machine:
   def start(self) -> bool:
     response = self.inner.patch(f'/machines/{self.id}/start')
     if response.status_code == 400 or self.status == 'ready':
-      logger.error('machine is already running')
+      print('machine is already running')
       return False
-    elif response.status_code != 200:
-      logger.error('Error while starting machine "%s": %s', self.id, response.json())
+    elif response.status_code != 200: raise ValueError(f'Error while starting machine: {response.json()}')
     return True
   def stop(self) -> bool:
     response = self.inner.patch(f'/machines/{self.id}/stop')
     if response.status_code == 400 or self.status == 'off':
-      logger.error('machine is already off')
+      print('machine is already off')
       return False
-    elif response.status_code != 200:
-      logger.error('Error while stopping machine "%s": %s', self.id, response.json())
+    elif response.status_code != 200: raise ValueError(f'Error while stopping machine {response.json()}')
     return True
+  @classmethod
+  def ci(cls, template_id: str):
+    client = httpx.Client(headers=HEADERS, base_url=API_URL, timeout=60)
+    machines = client.get('/machines', params=dict(limit=1, name='openllm-ci')).json()
+    if len(machines['items']) == 1:
+      return cls(id=machines['items'][0]['id'], inner=client)
+    response = client.post('/machines', json=dict(
+      name=f'openllm-ci-{datetime.datetime.now().timestamp()}',
+      machineType='A100-80G', templateId=template_id,
+      networkId=os.getenv("PAPERSPACE_NETWORK_ID"),
+      diskSize=500, region='ny2', publicIpType="dynamic", startOnCreate=True,
+    ))
+    if response.status_code != 200: raise ValueError(f'Failed while creating a machine: {response.json()}')
+    return cls(id=response.json()['data']['id'], inner=client)
+  def actions(self): return f'publicIp={self.metadata["publicIp"]}'
 
 def main():
   parser = argparse.ArgumentParser()
   group = parser.add_mutually_exclusive_group(required=True)
   group.add_argument('--start', metavar='ID')
   group.add_argument('--stop', metavar='ID')
+  group.add_argument('--delete', metavar='ID')
+  group.add_argument('--ci-template', metavar='ID')
   args = parser.parse_args()
 
-  if args.start:
+  if args.ci_template:
+    machine =  Machine.ci(args.ci_template)
+    while machine.status != 'ready': time.sleep(5)
+    print(machine.actions())
+    machine.close()
+  elif args.delete:
+    with httpx.Client(headers=HEADERS, base_url=API_URL, timeout=60) as client:
+      response = client.delete(f'/machines/{args.delete}')
+      if response.status_code != 200:
+        print('Error while deleting machine %s', response.json())
+        return 1
+  elif args.start:
     with Machine(id=args.start) as machine:
       if machine.start():
         while machine.status != 'ready':
-          logger.info('Waiting for machine "%s" to be ready...', machine.id)
+          print('Waiting for machine "%s" to be ready...', machine.id)
           time.sleep(5)
       else:
-        logger.error('Failed to start machine "%s"', machine.id)
+        print('Failed to start machine "%s"', machine.id)
         return 1
   elif args.stop:
     with Machine(id=args.stop) as machine:
       if machine.stop():
         while machine.status != 'ready':
-          logger.info('Waiting for machine "%s" to stop...', machine.id)
+          print('Waiting for machine "%s" to stop...', machine.id)
           time.sleep(5)
       else:
-        logger.error('Failed to stopmachine "%s"', machine.id)
+        print('Failed to stop machine "%s"', machine.id)
         return 1
   return 0
 

tools/requirements.txt

@@ -3,3 +3,4 @@ jupyter
 tomlkit
 ghapi
 pre-commit
+orjson