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

adding model-info and tokenize to the TC RHOAIENG-3483 #1281

Merged
merged 2 commits into from
Mar 13, 2024
Merged

adding model-info and tokenize to the TC RHOAIENG-3483 #1281

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4d30f14
adding model-info and tokenize to the TC RHOAIENG-3483
mwaykole Mar 13, 2024
b9160f3
Merge branch 'master' into tonken
mwaykole Mar 13, 2024
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
8 changes: 7 additions & 1 deletion ods_ci/tests/Resources/Files/llm/model_expected_responses.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,10 @@
"llama-2-13b-chat": {
"response_tokens": 20,
"response_text": "\n\nWater boils at 100 degrees Celsius or 212",
"streamed_response_text": "{ 'inputTokenCount': 10}{ 'generatedTokenCount': 2, 'text': '\n'}{ 'generatedTokenCount': 3, 'text': 'I a'}{ 'generatedTokenCount': 4, 'text': 'm no'}{ 'generatedTokenCount': 5, 'text': 't sur'}{ 'generatedTokenCount': 6, 'text': 'e i'}{ 'generatedTokenCount': 7, 'text': 'f thi'}{ 'generatedTokenCount': 8, 'text': 's i'}{ 'generatedTokenCount': 9, 'text': 's th'}{ 'generatedTokenCount': 10, 'text': 'e righ'}{ 'generatedTokenCount': 11, 'text': 't plac'}{ 'generatedTokenCount': 12, 'text': 'e t'}{ 'generatedTokenCount': 13, 'text': 'o as'}{ 'generatedTokenCount': 14, 'text': 'k thi'}{ 'generatedTokenCount': 15, 'text': 's questio'}{ 'generatedTokenCount': 16, 'text': 'n'}{ 'generatedTokenCount': 17, 'text': ', bu'}{ 'generatedTokenCount': 18, 'text': 't '}{ 'generatedTokenCount': 19, 'text': 'I a'}{ 'generatedTokenCount': 20, 'text': 'm trying', 'stopReason': 'MAX_TOKENS'}"
"streamed_response_text": "{ 'inputTokenCount': 10}{ 'generatedTokenCount': 2, 'text': '\n'}{ 'generatedTokenCount': 3, 'text': 'I a'}{ 'generatedTokenCount': 4, 'text': 'm no'}{ 'generatedTokenCount': 5, 'text': 't sur'}{ 'generatedTokenCount': 6, 'text': 'e i'}{ 'generatedTokenCount': 7, 'text': 'f thi'}{ 'generatedTokenCount': 8, 'text': 's i'}{ 'generatedTokenCount': 9, 'text': 's th'}{ 'generatedTokenCount': 10, 'text': 'e righ'}{ 'generatedTokenCount': 11, 'text': 't plac'}{ 'generatedTokenCount': 12, 'text': 'e t'}{ 'generatedTokenCount': 13, 'text': 'o as'}{ 'generatedTokenCount': 14, 'text': 'k thi'}{ 'generatedTokenCount': 15, 'text': 's questio'}{ 'generatedTokenCount': 16, 'text': 'n'}{ 'generatedTokenCount': 17, 'text': ', bu'}{ 'generatedTokenCount': 18, 'text': 't '}{ 'generatedTokenCount': 19, 'text': 'I a'}{ 'generatedTokenCount': 20, 'text': 'm trying', 'stopReason': 'MAX_TOKENS'}",
"tgis-runtime": {
"tokenize_response_text": "{'responses':[{'tokenCount':9,'tokens':['\\u003cs\\u003e','▁At','▁what','▁temperature','▁does','▁water','▁bo','il','?']}]}"
}
}
}
},
Expand Down Expand Up @@ -172,6 +175,9 @@
},
"mpt-7b-instruct2":{
"tgis-runtime": "{ 'maxSequenceLength': 2048, 'maxNewTokens': 1024 }"
},
"llama-2-13b-chat-hf":{
"tgis-runtime": "{ 'maxSequenceLength': 4096,'maxNewTokens': 1024}"
}
}
}
8 changes: 8 additions & 0 deletions ...ests/Tests/400__ods_dashboard/420__model_serving/LLMs/422__model_serving_llm_models.robot
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -345,6 +345,14 @@ Verify User Can Serve And Query A meta-llama/llama-2-13b-chat Model
... inference_type=streaming n_times=1 protocol=grpc
... namespace=${test_namespace} query_idx=0 validate_response=${FALSE}
... port_forwarding=${use_port_forwarding}
Query Model Multiple Times model_name=${model_name} runtime=${TGIS_RUNTIME_NAME}
... inference_type=model-info n_times=0
... namespace=${test_namespace} validate_response=${TRUE} string_check_only=${TRUE}
... port_forwarding=${use_port_forwarding}
Query Model Multiple Times model_name=${model_name} runtime=${TGIS_RUNTIME_NAME}
... inference_type=tokenize n_times=0 query_idx=0
... namespace=${test_namespace} validate_response=${TRUE} string_check_only=${TRUE}
... port_forwarding=${use_port_forwarding}
[Teardown] Run Keywords
... Clean Up Test Project test_ns=${test_namespace}
... isvc_names=${models_names} wait_prj_deletion=${FALSE}
Expand Down
Loading