Skip to content

Commit 8fe0cad

Browse files
committed
Update LMI djl version to 0.28.0 and Least Outstanding Request Strategy
1 parent 4265162 commit 8fe0cad

File tree

3 files changed

+12
-3
lines changed

3 files changed

+12
-3
lines changed

llama-2-lmi/llama-2-13b-chat/1-deploy-llama-2-13b-chat-lmi-response-streaming.ipynb

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -328,7 +328,7 @@
328328
"outputs": [],
329329
"source": [
330330
"inference_image_uri = image_uris.retrieve(\n",
331-
" framework=\"djl-deepspeed\", region=region, version=\"0.26.0\"\n",
331+
" framework=\"djl-deepspeed\", region=region, version=\"0.28.0\"\n",
332332
")\n",
333333
"inference_image_uri"
334334
]
@@ -492,6 +492,9 @@
492492
" \"InitialInstanceCount\": 1,\n",
493493
" \"ModelDataDownloadTimeoutInSeconds\": 3600,\n",
494494
" \"ContainerStartupHealthCheckTimeoutInSeconds\": 3600,\n",
495+
" \"RoutingConfig\": {\n",
496+
" 'RoutingStrategy': 'LEAST_OUTSTANDING_REQUESTS'\n",
497+
" }\n",
495498
" },\n",
496499
" ],\n",
497500
")\n",

llama-2-lmi/llama-2-70b-chat/1-deploy-llama-2-70b-chat-lmi-response-streaming.ipynb

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -326,7 +326,7 @@
326326
"outputs": [],
327327
"source": [
328328
"inference_image_uri = image_uris.retrieve(\n",
329-
" framework=\"djl-deepspeed\", region=region, version=\"0.26.0\"\n",
329+
" framework=\"djl-deepspeed\", region=region, version=\"0.28.0\"\n",
330330
")\n",
331331
"inference_image_uri"
332332
]
@@ -490,6 +490,9 @@
490490
" \"InitialInstanceCount\": 1,\n",
491491
" \"ModelDataDownloadTimeoutInSeconds\": 3600,\n",
492492
" \"ContainerStartupHealthCheckTimeoutInSeconds\": 3600,\n",
493+
" \"RoutingConfig\": {\n",
494+
" 'RoutingStrategy': 'LEAST_OUTSTANDING_REQUESTS'\n",
495+
" }\n",
493496
" },\n",
494497
" ],\n",
495498
")\n",

llama-2-lmi/llama-2-7b-chat/1-deploy-llama-2-7b-lmi-response-streaming.ipynb

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -336,7 +336,7 @@
336336
"outputs": [],
337337
"source": [
338338
"inference_image_uri = image_uris.retrieve(\n",
339-
" framework=\"djl-deepspeed\", region=region, version=\"0.26.0\"\n",
339+
" framework=\"djl-deepspeed\", region=region, version=\"0.28.0\"\n",
340340
")\n",
341341
"inference_image_uri"
342342
]
@@ -488,6 +488,9 @@
488488
" \"InitialInstanceCount\": 1,\n",
489489
" \"ModelDataDownloadTimeoutInSeconds\": 3600,\n",
490490
" \"ContainerStartupHealthCheckTimeoutInSeconds\": 3600,\n",
491+
" \"RoutingConfig\": {\n",
492+
" 'RoutingStrategy': 'LEAST_OUTSTANDING_REQUESTS'\n",
493+
" }\n",
491494
" },\n",
492495
" ],\n",
493496
")\n",

0 commit comments

Comments
 (0)