Skip to content

Revert "Remove model name override (#641)" #644

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

Merged
merged 1 commit into from
Oct 17, 2024
Merged

Revert "Remove model name override (#641)" #644

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
17 changes: 17 additions & 0 deletions model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,6 +143,7 @@

LLM_METADATA_KEY = "_llm"
RESERVED_METADATA_KEYS = [LLM_METADATA_KEY, CONVERTED_FROM_ARTIFACT_LIKE_KEY]
VLLM_MODEL_WEIGHTS_FOLDER = "model_files"

INFERENCE_FRAMEWORK_REPOSITORY: Dict[LLMInferenceFramework, str] = {
LLMInferenceFramework.DEEPSPEED: "instant-llm",
Expand Down Expand Up @@ -2792,6 +2793,10 @@ async def execute(

validate_endpoint_supports_openai_completion(model_endpoint, endpoint_content)

# if inference framework is VLLM, we need to set the model to use the weights folder
if endpoint_content.inference_framework == LLMInferenceFramework.VLLM:
request.model = VLLM_MODEL_WEIGHTS_FOLDER

inference_request = SyncEndpointPredictV1Request(
args=request.model_dump(exclude_none=True),
destination_path=OPENAI_COMPLETION_PATH,
Expand Down Expand Up @@ -2894,6 +2899,10 @@ async def execute(

validate_endpoint_supports_openai_completion(model_endpoint, model_content)

# if inference framework is VLLM, we need to set the model to use the weights folder
if model_content.inference_framework == LLMInferenceFramework.VLLM:
request.model = VLLM_MODEL_WEIGHTS_FOLDER

inference_request = SyncEndpointPredictV1Request(
args=request.model_dump(exclude_none=True),
destination_path=OPENAI_COMPLETION_PATH,
Expand Down Expand Up @@ -3051,6 +3060,10 @@ async def execute(

validate_endpoint_supports_chat_completion(model_endpoint, endpoint_content)

# if inference framework is VLLM, we need to set the model to use the weights folder
if endpoint_content.inference_framework == LLMInferenceFramework.VLLM:
request.model = VLLM_MODEL_WEIGHTS_FOLDER

inference_request = SyncEndpointPredictV1Request(
args=request.model_dump(exclude_none=True),
destination_path=OPENAI_CHAT_COMPLETION_PATH,
Expand Down Expand Up @@ -3152,6 +3165,10 @@ async def execute(
)
validate_endpoint_supports_chat_completion(model_endpoint, model_content)

# if inference framework is VLLM, we need to set the model to use the weights folder
if model_content.inference_framework == LLMInferenceFramework.VLLM:
request.model = VLLM_MODEL_WEIGHTS_FOLDER

inference_request = SyncEndpointPredictV1Request(
args=request.model_dump(exclude_none=True),
destination_path=OPENAI_CHAT_COMPLETION_PATH,
Expand Down