Update naming

Author: yinggeh

python/openai/openai_frontend/engine/triton_engine.py

@@ -244,7 +244,7 @@ async def chat(
         )
 
         usage = _get_usage_from_response(
-            response, metadata.backend, RequestKind.GENERATE
+            response, metadata.backend, RequestKind.GENERATION
         )
 
         return CreateChatCompletionResponse(
@@ -348,7 +348,7 @@ async def completion(
         text = _get_output(response)
 
         usage = _get_usage_from_response(
-            response, metadata.backend, RequestKind.GENERATE
+            response, metadata.backend, RequestKind.GENERATION
         )
 
         choice = Choice(
@@ -392,7 +392,9 @@ async def embedding(
         embedding_json = _get_output(response)
         embedding_list = json.loads(embedding_json)
 
-        usage = _get_usage_from_response(response, metadata.backend, RequestKind.EMBED)
+        usage = _get_usage_from_response(
+            response, metadata.backend, RequestKind.EMBEDDING
+        )
 
         embedding = self._get_embedding(embedding_list, request.encoding_format)
         embedding_obj = EmbeddingObject(
@@ -433,14 +435,14 @@ def _determine_request_converter(self, backend: str, request_type: RequestKind):
 
         # Request conversion from OpenAI format to backend-specific format
         if backend == "vllm":
-            if request_type == RequestKind.GENERATE:
+            if request_type == RequestKind.GENERATION:
                 return _create_vllm_generate_request
             else:
                 return _create_vllm_embedding_request
 
         # Use TRT-LLM format as default for everything else. This could be
         # an ensemble, a python or BLS model, a TRT-LLM backend model, etc.
-        if request_type == RequestKind.GENERATE:
+        if request_type == RequestKind.GENERATION:
             return _create_trtllm_generate_request
         else:
             return _create_trtllm_embedding_request
@@ -489,10 +491,10 @@ def _get_model_metadata(self) -> Dict[str, TritonModelMetadata]:
                 lora_names=lora_names,
                 create_time=self.create_time,
                 inference_request_converter=self._determine_request_converter(
-                    backend, RequestKind.GENERATE
+                    backend, RequestKind.GENERATION
                 ),
                 embedding_request_converter=self._determine_request_converter(
-                    backend, RequestKind.EMBED
+                    backend, RequestKind.EMBEDDING
                 ),
             )
             model_metadata[name] = metadata

python/openai/openai_frontend/engine/utils/triton.py

@@ -47,8 +47,8 @@
 
 
 class RequestKind(Enum):
-    GENERATE = 1
-    EMBED = 2
+    GENERATION = 1
+    EMBEDDING = 2
 
 
 def _create_vllm_generate_request(
@@ -273,7 +273,7 @@ class _StreamingUsageAccumulator:
 
     def update(self, response: tritonserver.InferenceResponse):
         """Extracts usage from a response and updates the token counts."""
-        usage = _get_usage_from_response(response, self.backend, RequestKind.GENERATE)
+        usage = _get_usage_from_response(response, self.backend, RequestKind.GENERATION)
         if usage:
             # The prompt_tokens is received with every chunk but should only be set once.
             if not self._prompt_tokens_set:
@@ -332,14 +332,14 @@ def _get_usage_from_response(
             completion_tokens = completion_tokens_ptr[0]
 
         if prompt_tokens is not None:
-            if request_type == RequestKind.GENERATE and completion_tokens is not None:
+            if request_type == RequestKind.GENERATION and completion_tokens is not None:
                 total_tokens = prompt_tokens + completion_tokens
                 return CompletionUsage(
                     prompt_tokens=prompt_tokens,
                     completion_tokens=completion_tokens,
                     total_tokens=total_tokens,
                 )
-            elif request_type == RequestKind.EMBED:
+            elif request_type == RequestKind.EMBEDDING:
                 return EmbeddingUsage(
                     prompt_tokens=prompt_tokens,
                     total_tokens=prompt_tokens,