Change GPU Runners (#7840)

* Move to new GPU Runners for slow tests

* Move to new GPU Runners for nightly tests

.github/workflows/nightly_tests.yml

@@ -112,7 +112,7 @@ jobs:
 
   run_nightly_tests_for_other_torch_modules:
     name: Torch Non-Pipelines CUDA Nightly Tests
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
@@ -185,7 +185,7 @@ jobs:
 
   run_lora_nightly_tests:
     name: Nightly LoRA Tests with PEFT and TORCH
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
@@ -298,7 +298,7 @@ jobs:
 
   run_nightly_onnx_tests:
     name: Nightly ONNXRuntime CUDA tests on Ubuntu
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-onnxruntime-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/

.github/workflows/push_tests.yml

@@ -116,7 +116,7 @@ jobs:
 
   torch_cuda_tests:
     name: Torch CUDA Tests
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
@@ -168,7 +168,7 @@ jobs:
 
   peft_cuda_tests:
     name: PEFT CUDA Tests
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
@@ -265,7 +265,7 @@ jobs:
 
   onnx_cuda_tests:
     name: ONNX CUDA Tests
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-onnxruntime-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
@@ -313,7 +313,7 @@ jobs:
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-compile-cuda
@@ -354,7 +354,7 @@ jobs:
   run_xformers_tests:
     name: PyTorch xformers CUDA tests
 
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-xformers-cuda
@@ -395,7 +395,7 @@ jobs:
   run_examples_tests:
     name: Examples PyTorch CUDA tests on Ubuntu
 
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-cuda