xiaohei/model_garden
1
0
Fork 0
mirror of https://github.com/GoogleCloudPlatform/vertex-ai-samples.git synced 2026-09-26 14:42:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Set model_garden_source_model_name for model_garden_phi4_deployment notebook.

Browse Source 
PiperOrigin-RevId: 722840147
This commit is contained in:
Dustin Luong
2025-02-03 16:25:21 -08:00
committed by Copybara-Service
parent 711a4f0b8c
commit abdd887fa1
1 changed files with 14 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/community/model_garden/model_garden_phi4_deployment.ipynb
+14
View File
@@ -258,6 +258,8 @@
"def deploy_model_vllm(\n",
" model_name: str,\n",
" model_id: str,\n",
" publisher: str,\n",
" publisher_model_id: str,\n",
" service_account: str,\n",
" base_model_id: str = None,\n",
" machine_type: str = \"g2-standard-8\",\n",
@@ -351,6 +353,9 @@
" serving_container_environment_variables=env_vars,\n",
" serving_container_shared_memory_size_mb=(16 * 1024), # 16 GB\n",
" serving_container_deployment_timeout=7200,\n",
" model_garden_source_model_name=(\n",
" f\"publishers/{publisher}/models/{publisher_model_id}\"\n",
" ),\n",
" )\n",
" print(\n",
" f\"Deploying {model_name} on {machine_type} with {accelerator_count} {accelerator_type} GPU(s).\"\n",
@@ -378,6 +383,8 @@
"models[\"vllm_gpu\"], endpoints[\"vllm_gpu\"] = deploy_model_vllm(\n",
" model_name=common_util.get_job_name_with_datetime(prefix=MODEL_ID),\n",
" model_id=model_id,\n",
" publisher=\"microsoft\",\n",
" publisher_model_id=\"phi-4\",\n",
" service_account=SERVICE_ACCOUNT,\n",
" machine_type=machine_type,\n",
" accelerator_type=accelerator_type,\n",
@@ -531,6 +538,8 @@
"def deploy_model_hexllm(\n",
" model_name: str,\n",
" model_id: str,\n",
" publisher: str,\n",
" publisher_model_id: str,\n",
" service_account: str,\n",
" base_model_id: str = None,\n",
" data_parallel_size: int = 1,\n",
@@ -610,6 +619,9 @@
" serving_container_shared_memory_size_mb=(16 * 1024), # 16 GB\n",
" serving_container_deployment_timeout=7200,\n",
" location=TPU_DEPLOYMENT_REGION,\n",
" model_garden_source_model_name=(\n",
" f\"publishers/{publisher}/models/{publisher_model_id}\"\n",
" ),\n",
" )\n",
"\n",
" model.deploy(\n",
@@ -634,6 +646,8 @@
"models[\"hexllm_tpu\"], endpoints[\"hexllm_tpu\"] = deploy_model_hexllm(\n",
" model_name=common_util.get_job_name_with_datetime(prefix=MODEL_ID),\n",
" model_id=model_id,\n",
" publisher=\"microsoft\",\n",
" publisher_model_id=\"phi-4\",\n",
" service_account=SERVICE_ACCOUNT,\n",
" tensor_parallel_size=tensor_parallel_size,\n",
" machine_type=machine_type,\n",