Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update chat completions URL for dedicated endpoint in Gemma and Llama deployment notebooks. #3659

Merged
merged 1 commit into from
Oct 18, 2024
Merged

Update chat completions URL for dedicated endpoint in Gemma and Llama deployment notebooks. #3659

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 19 additions & 0 deletions notebooks/community/model_garden/model_garden_gemma_deployment_on_vertex.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -482,6 +482,8 @@
"_region = REGION\n",
"REGION = TPU_DEPLOYMENT_REGION\n",
"\n",
"if use_dedicated_endpoint:\n",
" DEDICATED_ENDPOINT_DNS = endpoints[\"hexllm_tpu\"].gca_resource.dedicated_endpoint_dns\n",
"ENDPOINT_RESOURCE_NAME = \"projects/{}/locations/{}/endpoints/{}\".format(\n",
" PROJECT_ID, REGION, endpoints[\"hexllm_tpu\"].name\n",
")\n",
Expand Down Expand Up @@ -513,6 +515,12 @@
"BASE_URL = (\n",
" f\"https://{REGION}-aiplatform.googleapis.com/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
")\n",
"try:\n",
" if use_dedicated_endpoint:\n",
" BASE_URL = f\"https://{DEDICATED_ENDPOINT_DNS}/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
"except NameError:\n",
" pass\n",
"\n",
"client = openai.OpenAI(base_url=BASE_URL, api_key=creds.token)\n",
"\n",
"model_response = client.chat.completions.create(\n",
Expand Down Expand Up @@ -624,6 +632,9 @@
"# Note that a larger max_model_len will require more GPU memory.\n",
"max_model_len = 2048\n",
"\n",
"# @markdown Set use_dedicated_endpoint to False if you don't want to use [dedicated endpoint](https://cloud.google.com/vertex-ai/docs/general/deployment#create-dedicated-endpoint).\n",
"use_dedicated_endpoint = True # @param {type:\"boolean\"}\n",
"\n",
"\n",
"def deploy_model_vllm(\n",
" model_name: str,\n",
Expand Down Expand Up @@ -823,6 +834,8 @@
"\n",
"# @markdown You can build chat applications with the instruction-tuned Gemma models.\n",
"\n",
"if use_dedicated_endpoint:\n",
" DEDICATED_ENDPOINT_DNS = endpoints[\"vllm_gpu\"].gca_resource.dedicated_endpoint_dns\n",
"ENDPOINT_RESOURCE_NAME = \"projects/{}/locations/{}/endpoints/{}\".format(\n",
" PROJECT_ID, REGION, endpoints[\"vllm_gpu\"].name\n",
")\n",
Expand Down Expand Up @@ -854,6 +867,12 @@
"BASE_URL = (\n",
" f\"https://{REGION}-aiplatform.googleapis.com/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
")\n",
"try:\n",
" if use_dedicated_endpoint:\n",
" BASE_URL = f\"https://{DEDICATED_ENDPOINT_DNS}/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
"except NameError:\n",
" pass\n",
"\n",
"client = openai.OpenAI(base_url=BASE_URL, api_key=creds.token)\n",
"\n",
"model_response = client.chat.completions.create(\n",
Expand Down
12 changes: 12 additions & 0 deletions notebooks/community/model_garden/model_garden_pytorch_llama3_1_deployment.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -535,6 +535,12 @@
"BASE_URL = (\n",
" f\"https://{REGION}-aiplatform.googleapis.com/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
")\n",
"try:\n",
" if use_dedicated_endpoint:\n",
" BASE_URL = f\"https://{DEDICATED_ENDPOINT_DNS}/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
"except NameError:\n",
" pass\n",
"\n",
"client = openai.OpenAI(base_url=BASE_URL, api_key=creds.token)\n",
"\n",
"model_response = client.chat.completions.create(\n",
Expand Down Expand Up @@ -834,6 +840,12 @@
"BASE_URL = (\n",
" f\"https://{REGION}-aiplatform.googleapis.com/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
")\n",
"try:\n",
" if use_dedicated_endpoint:\n",
" BASE_URL = f\"https://{DEDICATED_ENDPOINT_DNS}/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
"except NameError:\n",
" pass\n",
"\n",
"client = openai.OpenAI(base_url=BASE_URL, api_key=creds.token)\n",
"\n",
"model_response = client.chat.completions.create(\n",
Expand Down
18 changes: 18 additions & 0 deletions notebooks/community/model_garden/model_garden_pytorch_llama3_2_deployment.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -523,6 +523,12 @@
"BASE_URL = (\n",
" f\"https://{REGION}-aiplatform.googleapis.com/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
")\n",
"try:\n",
" if use_dedicated_endpoint:\n",
" BASE_URL = f\"https://{DEDICATED_ENDPOINT_DNS}/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
"except NameError:\n",
" pass\n",
"\n",
"client = openai.OpenAI(base_url=BASE_URL, api_key=creds.token)\n",
"\n",
"model_response = client.chat.completions.create(\n",
Expand Down Expand Up @@ -759,6 +765,12 @@
"BASE_URL = (\n",
" f\"https://{REGION}-aiplatform.googleapis.com/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
")\n",
"try:\n",
" if use_dedicated_endpoint:\n",
" BASE_URL = f\"https://{DEDICATED_ENDPOINT_DNS}/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
"except NameError:\n",
" pass\n",
"\n",
"client = openai.OpenAI(base_url=BASE_URL, api_key=creds.token)\n",
"\n",
"model_response = client.chat.completions.create(\n",
Expand Down Expand Up @@ -815,6 +827,12 @@
"BASE_URL = (\n",
" f\"https://{REGION}-aiplatform.googleapis.com/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
")\n",
"try:\n",
" if use_dedicated_endpoint:\n",
" BASE_URL = f\"https://{DEDICATED_ENDPOINT_DNS}/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
"except NameError:\n",
" pass\n",
"\n",
"client = openai.OpenAI(base_url=BASE_URL, api_key=creds.token)\n",
"\n",
"model_response = client.chat.completions.create(\n",
Expand Down
6 changes: 6 additions & 0 deletions notebooks/community/model_garden/model_garden_pytorch_llama3_deployment.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -530,6 +530,12 @@
"BASE_URL = (\n",
" f\"https://{REGION}-aiplatform.googleapis.com/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
")\n",
"try:\n",
" if use_dedicated_endpoint:\n",
" BASE_URL = f\"https://{DEDICATED_ENDPOINT_DNS}/v1beta1/{ENDPOINT_RESOURCE_NAME}\"\n",
"except NameError:\n",
" pass\n",
"\n",
"client = openai.OpenAI(base_url=BASE_URL, api_key=creds.token)\n",
"\n",
"model_response = client.chat.completions.create(\n",
Expand Down