switch to v100 (#2301)

Author: clee2000

.circleci/config.yml

@@ -204,7 +204,7 @@ jobs:
     resource_class: gpu.nvidia.small.multi
   pytorch_tutorial_pr_build_worker_1:
     <<: *pytorch_tutorial_build_worker_defaults
-    resource_class: gpu.nvidia.medium
+    resource_class: gpu.nvidia.large
   pytorch_tutorial_pr_build_worker_10:
     <<: *pytorch_tutorial_build_worker_defaults
   pytorch_tutorial_pr_build_worker_11:
@@ -249,7 +249,7 @@ jobs:
     resource_class: gpu.nvidia.small.multi
   pytorch_tutorial_trunk_build_worker_1:
     <<: *pytorch_tutorial_build_worker_defaults
-    resource_class: gpu.nvidia.medium
+    resource_class: gpu.nvidia.large
   pytorch_tutorial_trunk_build_worker_10:
     <<: *pytorch_tutorial_build_worker_defaults
   pytorch_tutorial_trunk_build_worker_11:

.circleci/regenerate.py

@@ -27,19 +27,19 @@ def jobs(pr_or_trunk, num_workers=20, indentation=2):
     jobs = {}
 
     # all tutorials that need gpu.nvidia.small.multi machines will be routed by
-    # get_files_to_run.py to 0th worker, similarly for gpu.nvidia.medium and the
+    # get_files_to_run.py to 0th worker, similarly for gpu.nvidia.large and the
     # 1st worker
     needs_gpu_nvidia_small_multi = [0]
-    needs_gpu_nvidia_medium = [1]
+    needs_gpu_nvidia_large = [1]
     jobs[f"pytorch_tutorial_{pr_or_trunk}_build_manager"] = {
         "<<": "*pytorch_tutorial_build_manager_defaults"
     }
     for i in range(num_workers):
         job_info = {"<<": "*pytorch_tutorial_build_worker_defaults"}
         if i in needs_gpu_nvidia_small_multi:
             job_info["resource_class"] = "gpu.nvidia.small.multi"
-        if i in needs_gpu_nvidia_medium:
-            job_info["resource_class"] = "gpu.nvidia.medium"
+        if i in needs_gpu_nvidia_large:
+            job_info["resource_class"] = "gpu.nvidia.large"
         jobs[f"pytorch_tutorial_{pr_or_trunk}_build_worker_{i}"] = job_info
 
     return indent(indentation, jobs).replace("'", "")

.jenkins/get_files_to_run.py

@@ -44,15 +44,15 @@ def add_to_shard(i, filename):
         filter(lambda x: get_needs_machine(x) == "gpu.nvidia.small.multi", all_files,)
     )
     needs_gpu_nvidia_medium = list(
-        filter(lambda x: get_needs_machine(x) == "gpu.nvidia.medium", all_files,)
+        filter(lambda x: get_needs_machine(x) == "gpu.nvidia.large", all_files,)
     )
     for filename in needs_gpu_nvidia_small_multi:
         # currently, the only job that uses gpu.nvidia.small.multi is the 0th worker,
         # so we'll add all the jobs that need this machine to the 0th worker
         add_to_shard(0, filename)
         all_other_files.remove(filename)
     for filename in needs_gpu_nvidia_medium:
-        # currently, the only job that uses gpu.nvidia.medium is the 1st worker,
+        # currently, the only job that uses gpu.nvidia.large is the 1st worker,
         # so we'll add all the jobs that need this machine to the 1st worker
         add_to_shard(1, filename)
         all_other_files.remove(filename)

.jenkins/metadata.json

@@ -26,6 +26,6 @@
     "needs": "gpu.nvidia.small.multi"
   },
   "intermediate_source/torch_compile_tutorial.py": {
-    "needs": "gpu.nvidia.medium"
+    "needs": "gpu.nvidia.large"
   }
 }