Add compute validations (#2371)

* Add compute validations * fix formatting
Azure · Jun 14, 2023 · d93f9cb · d93f9cb
1 parent af1f3d3
commit d93f9cb
Show file tree

Hide file tree

Showing 5 changed files with 68 additions and 8 deletions.
diff --git a/sdk/python/foundation-models/system/finetune/question-answering/extractive-qa.ipynb b/sdk/python/foundation-models/system/finetune/question-answering/extractive-qa.ipynb
@@ -122,10 +122,10 @@
     "        gpu_count_found = True\n",
     "# if gpu_count_found not found, then print an error\n",
     "if gpu_count_found:\n",
-    "    print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
+    "    print(f\"Number of GPU's in compute {compute.size}: {gpus_per_node}\")\n",
     "else:\n",
     "    raise ValueError(\n",
-    "        f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
+    "        f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
     "        f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
     "    )\n",
     "# CPU based finetune works only for single-node single-process\n",
@@ -135,6 +135,18 @@
     "    )\n",
     "    gpus_per_node = 1\n",
     "\n",
+    "# Computes with K80 GPUs are not supported\n",
+    "unsupported_gpu_vm_list = [\n",
+    "    \"standard_nc6\",\n",
+    "    \"standard_nc12\",\n",
+    "    \"standard_nc24\",\n",
+    "    \"standard_nc24r\",\n",
+    "]\n",
+    "if compute.size.lower() in unsupported_gpu_vm_list:\n",
+    "    raise ValueError(\n",
+    "        f\"VM size {compute.size} is currently not supported for finetuning\"\n",
+    "    )\n",
+    "\n",
     "# genrating a unique timestamp that can be used for names and versions that need to be unique\n",
     "timestamp = str(int(time.time()))"
    ]

diff --git a/sdk/python/foundation-models/system/finetune/summarization/news-summary.ipynb b/sdk/python/foundation-models/system/finetune/summarization/news-summary.ipynb
@@ -121,10 +121,10 @@
     "        gpu_count_found = True\n",
     "# if gpu_count_found not found, then print an error\n",
     "if gpu_count_found:\n",
-    "    print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
+    "    print(f\"Number of GPU's in compute {compute.size}: {gpus_per_node}\")\n",
     "else:\n",
     "    raise ValueError(\n",
-    "        f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
+    "        f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
     "        f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
     "    )\n",
     "# CPU based finetune works only for single-node single-process\n",
@@ -134,6 +134,18 @@
     "    )\n",
     "    gpus_per_node = 1\n",
     "\n",
+    "# Computes with K80 GPUs are not supported\n",
+    "unsupported_gpu_vm_list = [\n",
+    "    \"standard_nc6\",\n",
+    "    \"standard_nc12\",\n",
+    "    \"standard_nc24\",\n",
+    "    \"standard_nc24r\",\n",
+    "]\n",
+    "if compute.size.lower() in unsupported_gpu_vm_list:\n",
+    "    raise ValueError(\n",
+    "        f\"VM size {compute.size} is currently not supported for finetuning\"\n",
+    "    )\n",
+    "\n",
     "# genrating a unique timestamp that can be used for names and versions that need to be unique\n",
     "timestamp = str(int(time.time()))"
    ]

diff --git a/sdk/python/foundation-models/system/finetune/text-classification/emotion-detection.ipynb b/sdk/python/foundation-models/system/finetune/text-classification/emotion-detection.ipynb
@@ -122,10 +122,10 @@
     "        gpu_count_found = True\n",
     "# if gpu_count_found not found, then print an error\n",
     "if gpu_count_found:\n",
-    "    print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
+    "    print(f\"Number of GPU's in compute {compute.size}: {gpus_per_node}\")\n",
     "else:\n",
     "    raise ValueError(\n",
-    "        f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
+    "        f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
     "        f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
     "    )\n",
     "# CPU based finetune works only for single-node single-process\n",
@@ -135,6 +135,18 @@
     "    )\n",
     "    gpus_per_node = 1\n",
     "\n",
+    "# Computes with K80 GPUs are not supported\n",
+    "unsupported_gpu_vm_list = [\n",
+    "    \"standard_nc6\",\n",
+    "    \"standard_nc12\",\n",
+    "    \"standard_nc24\",\n",
+    "    \"standard_nc24r\",\n",
+    "]\n",
+    "if compute.size.lower() in unsupported_gpu_vm_list:\n",
+    "    raise ValueError(\n",
+    "        f\"VM size {compute.size} is currently not supported for finetuning\"\n",
+    "    )\n",
+    "\n",
     "# generating a unique timestamp that can be used for names and versions that need to be unique\n",
     "timestamp = str(int(time.time()))"
    ]

diff --git a/sdk/python/foundation-models/system/finetune/token-classification/token-classification.ipynb b/sdk/python/foundation-models/system/finetune/token-classification/token-classification.ipynb
@@ -125,7 +125,7 @@
     "    print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
     "else:\n",
     "    raise ValueError(\n",
-    "        f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
+    "        f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
     "        f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
     "    )\n",
     "# CPU based finetune works only for single-node single-process\n",
@@ -135,6 +135,18 @@
     "    )\n",
     "    gpus_per_node = 1\n",
     "\n",
+    "# Computes with K80 GPUs are not supported\n",
+    "unsupported_gpu_vm_list = [\n",
+    "    \"standard_nc6\",\n",
+    "    \"standard_nc12\",\n",
+    "    \"standard_nc24\",\n",
+    "    \"standard_nc24r\",\n",
+    "]\n",
+    "if compute.size.lower() in unsupported_gpu_vm_list:\n",
+    "    raise ValueError(\n",
+    "        f\"VM size {compute.size} is currently not supported for finetuning\"\n",
+    "    )\n",
+    "\n",
     "# genrating a unique timestamp that can be used for names and versions that need to be unique\n",
     "timestamp = str(int(time.time()))"
    ]

diff --git a/sdk/python/foundation-models/system/finetune/translation/translation.ipynb b/sdk/python/foundation-models/system/finetune/translation/translation.ipynb
@@ -124,7 +124,7 @@
     "    print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
     "else:\n",
     "    raise ValueError(\n",
-    "        f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
+    "        f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
     "        f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
     "    )\n",
     "# CPU based finetune works only for single-node single-process\n",
@@ -134,6 +134,18 @@
     "    )\n",
     "    gpus_per_node = 1\n",
     "\n",
+    "# Computes with K80 GPUs are not supported\n",
+    "unsupported_gpu_vm_list = [\n",
+    "    \"standard_nc6\",\n",
+    "    \"standard_nc12\",\n",
+    "    \"standard_nc24\",\n",
+    "    \"standard_nc24r\",\n",
+    "]\n",
+    "if compute.size.lower() in unsupported_gpu_vm_list:\n",
+    "    raise ValueError(\n",
+    "        f\"VM size {compute.size} is currently not supported for finetuning\"\n",
+    "    )\n",
+    "\n",
     "# genrating a unique timestamp that can be used for names and versions that need to be unique\n",
     "timestamp = str(int(time.time()))"
    ]