Skip to content

Commit 1559cdb

Browse files
committed
Upgrade HF Image URI 2.0.2 & Least Outstanding Requests Strategy
1 parent 8fe0cad commit 1559cdb

File tree

3 files changed

+12
-3
lines changed

3 files changed

+12
-3
lines changed

llama-2-hf-tgi/llama-2-13b-chat-hf/1-deploy-llama-2-13b-chat-hf-tgi-sagemaker.ipynb

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -135,7 +135,7 @@
135135
"# retrieve the llm image uri\n",
136136
"llm_image = get_huggingface_llm_image_uri(\n",
137137
" \"huggingface\",\n",
138-
" version=\"1.0.3\"\n",
138+
" version=\"2.0.2\"\n",
139139
")\n",
140140
"\n",
141141
"# print ecr image uri\n",
@@ -244,6 +244,9 @@
244244
" initial_instance_count=1,\n",
245245
" instance_type=instance_type,\n",
246246
" container_startup_health_check_timeout=health_check_timeout,\n",
247+
" routing_config = {\n",
248+
" \"RoutingStrategy\": sagemaker.enums.RoutingStrategy.LEAST_OUTSTANDING_REQUESTS\n",
249+
" }\n",
247250
")"
248251
]
249252
},

llama-2-hf-tgi/llama-2-70b-chat-hf/1-deploy-llama-2-70b-chat-hf-tgi-sagemaker.ipynb

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -135,7 +135,7 @@
135135
"# retrieve the llm image uri\n",
136136
"llm_image = get_huggingface_llm_image_uri(\n",
137137
" \"huggingface\",\n",
138-
" version=\"1.0.3\"\n",
138+
" version=\"2.0.2\"\n",
139139
")\n",
140140
"\n",
141141
"# print ecr image uri\n",
@@ -246,6 +246,9 @@
246246
" initial_instance_count=1,\n",
247247
" instance_type=instance_type,\n",
248248
" container_startup_health_check_timeout=health_check_timeout,\n",
249+
" routing_config = {\n",
250+
" \"RoutingStrategy\": sagemaker.enums.RoutingStrategy.LEAST_OUTSTANDING_REQUESTS\n",
251+
" }\n",
249252
")"
250253
]
251254
},

llama-2-hf-tgi/llama-2-7b-chat-hf/1-deploy-llama-2-7b-chat-hf-tgi-sagemaker.ipynb

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -135,7 +135,7 @@
135135
"# retrieve the llm image uri\n",
136136
"llm_image = get_huggingface_llm_image_uri(\n",
137137
" \"huggingface\",\n",
138-
" version=\"1.0.3\"\n",
138+
" version=\"2.0.2\"\n",
139139
")\n",
140140
"\n",
141141
"# print ecr image uri\n",
@@ -244,6 +244,9 @@
244244
" initial_instance_count=1,\n",
245245
" instance_type=instance_type,\n",
246246
" container_startup_health_check_timeout=health_check_timeout,\n",
247+
" routing_config = {\n",
248+
" \"RoutingStrategy\": sagemaker.enums.RoutingStrategy.LEAST_OUTSTANDING_REQUESTS\n",
249+
" }\n",
247250
")"
248251
]
249252
},

0 commit comments

Comments
 (0)