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

Weekly update the vllm/hf-tei/hf-inference-toolkit containers.

Browse Source 
PiperOrigin-RevId: 819784960
This commit is contained in:
Vertex MG Team
2025-10-15 09:16:29 -07:00
committed by Copybara-Service
parent b1dfac2043
commit 424400bace
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/community/model_garden/model_garden_huggingface_pytorch_inference_deployment.ipynb
+1 -1
View File
@@ -163,7 +163,7 @@
"TASK = \"text-classification\" # @param {type: \"string\", isTemplate: true}\n",
"\n",
"# The pre-built serving docker images for Hugging Face Pytorch Inference.\n",
"SERVE_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/vertex-model-garden/hf-inference-toolkit.cu125.0-1.ubuntu2204.py311:model-garden.hf-inference-toolkit-0-1-release_20251004.00_p0\"\n",
"SERVE_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/vertex-model-garden/hf-inference-toolkit.cu125.0-1.ubuntu2204.py311:model-garden.hf-inference-toolkit-0-1-release_20251013.00_p0\"\n",
"\n",
"machine_type = \"g2-standard-8\" # @param {type: \"string\", isTemplate: true}\n",
"accelerator_type = \"NVIDIA_L4\" # @param [\"NVIDIA_L4\", \"None\"] {isTemplate: true}\n",
notebooks/community/model_garden/model_garden_huggingface_tei_deployment.ipynb
+1 -1
View File
@@ -214,7 +214,7 @@
"HUGGING_FACE_MODEL_ID = \"Qwen/Qwen3-Embedding-8B\" # @param {type: \"string\", isTemplate: true}\n",
"\n",
"# The pre-built serving docker images for TEI.\n",
"TEI_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/vertex-model-garden/hf-tei.cu125.0-1.ubuntu2204.py310:model-garden.hf-tei-0-1-release_20251003.00_p0\"\n",
"TEI_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/vertex-model-garden/hf-tei.cu125.0-1.ubuntu2204.py310:model-garden.hf-tei-0-1-release_20251010.00_p0\"\n",
"\n",
"machine_type = \"g2-standard-8\" # @param {type: \"string\", isTemplate: true}\n",
"accelerator_type = \"NVIDIA_L4\" # @param [\"NVIDIA_L4\", \"None\"] {isTemplate: true}\n",
notebooks/community/model_garden/model_garden_huggingface_vllm_deployment.ipynb
+1 -1
View File
@@ -164,7 +164,7 @@
"HF_TOKEN = \"\" # @param {type:\"string\", isTemplate: true}\n",
"\n",
"# The pre-built vLLM serving docker image.\n",
"VLLM_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20251003_0916_RC01\"\n",
"VLLM_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20251010_0916_RC01\"\n",
"SERVING_CONTAINER_IMAGE_URI = VLLM_DOCKER_URI\n",
"LABEL = \"vllm\"\n",
"\n",