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

Add default score file for non hftgi #2552

Merged
merged 5 commits into from
Aug 11, 2023
Merged

Add default score file for non hftgi #2552

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f68c015
add default score file for non hftgi
Aug 11, 2023
d871d25
rev
Aug 11, 2023
5c7570e
black
Aug 11, 2023
e67645b
add excount
Aug 11, 2023
2f7c330
Merge branch 'main' into gks/llama70bfixes
srsaggam Aug 11, 2023
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
13 changes: 13 additions & 0 deletions ...hon/foundation-models/system/inference/text-generation/llama-safe-online-deployment.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,12 +298,16 @@
" reg_client.models.list(model_name)\n",
") # list available versions of the model\n",
"llama_model = None\n",
"hf_tgi = False # If text-generation-inference (hf container) is supported for model\n",
"\n",
"if len(version_list) == 0:\n",
" raise Exception(f\"No model named {model_name} found in registry\")\n",
"else:\n",
" model_version = version_list[0].version\n",
" llama_model = reg_client.models.get(model_name, model_version)\n",
" if \"inference_supported_envs\" in llama_model.tags:\n",
" if \"hf_tgi\" in llama_model.tags[\"inference_supported_envs\"]:\n",
" hf_tgi = True\n",
" print(\n",
" f\"Using model name: {llama_model.name}, version: {llama_model.version}, id: {llama_model.id} for inferencing\"\n",
" )"
Expand Down Expand Up @@ -448,16 +452,25 @@
"source": [
"from azure.ai.ml.entities import (\n",
" OnlineRequestSettings,\n",
" CodeConfiguration,\n",
" ManagedOnlineDeployment,\n",
" ProbeSettings,\n",
")\n",
"\n",
"# For HF TGI inferencing, the scoring script is baked into the container\n",
"code_configuration = (\n",
" CodeConfiguration(code=\"./llama-files/score/default/\", scoring_script=\"score.py\")\n",
" if not hf_tgi\n",
" else None\n",
")\n",
"\n",
"deployment = ManagedOnlineDeployment(\n",
" name=deployment_name,\n",
" endpoint_name=endpoint_name,\n",
" model=llama_model.id,\n",
" instance_type=sku_name,\n",
" instance_count=1,\n",
" code_configuration=code_configuration,\n",
" environment_variables=deployment_env_vars,\n",
" request_settings=OnlineRequestSettings(request_timeout_ms=REQUEST_TIMEOUT_MS),\n",
" liveness_probe=ProbeSettings(\n",
Expand Down
Loading