squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Frontend] Adjust try/except blocks in API impl (#10056)

Browse Source 
Signed-off-by: Nick Hill <nhill@redhat.com>
This commit is contained in:
Nick Hill 2024-11-07 04:07:51 +00:00 committed by GitHub
parent d3859f1891
commit 29862b884b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/entrypoints/openai/serving_completion.py
View File

@ -189,13 +189,7 @@ class OpenAIServingCompletion(OpenAIServing):
try: try:
async for i, res in result_generator: async for i, res in result_generator:
final_res_batch[i] = res final_res_batch[i] = res
except asyncio.CancelledError:
return self.create_error_response("Client disconnected")
except ValueError as e:
# TODO: Use a vllm-specific Validation Error
return self.create_error_response(str(e))
try:
for i, final_res in enumerate(final_res_batch): for i, final_res in enumerate(final_res_batch):
assert final_res is not None assert final_res is not None
@ -217,6 +211,8 @@ class OpenAIServingCompletion(OpenAIServing):
tokenizer, tokenizer,
request_metadata, request_metadata,
) )
except asyncio.CancelledError:
return self.create_error_response("Client disconnected")
except ValueError as e: except ValueError as e:
# TODO: Use a vllm-specific Validation Error # TODO: Use a vllm-specific Validation Error
return self.create_error_response(str(e)) return self.create_error_response(str(e))

8
vllm/entrypoints/openai/serving_embedding.py
View File

@ -205,12 +205,8 @@ class OpenAIServingEmbedding(OpenAIServing):
try: try:
async for i, res in result_generator: async for i, res in result_generator:
final_res_batch[i] = res final_res_batch[i] = res
except asyncio.CancelledError:
return self.create_error_response("Client disconnected")
try: assert all(final_res is not None for final_res in final_res_batch)
for final_res in final_res_batch:
assert final_res is not None
final_res_batch_checked = cast(List[EmbeddingRequestOutput], final_res_batch_checked = cast(List[EmbeddingRequestOutput],
final_res_batch) final_res_batch)
@ -218,6 +214,8 @@ class OpenAIServingEmbedding(OpenAIServing):
response = request_output_to_embedding_response( response = request_output_to_embedding_response(
final_res_batch_checked, request_id, created_time, model_name, final_res_batch_checked, request_id, created_time, model_name,
encoding_format) encoding_format)
except asyncio.CancelledError:
return self.create_error_response("Client disconnected")
except ValueError as e: except ValueError as e:
# TODO: Use a vllm-specific Validation Error # TODO: Use a vllm-specific Validation Error
return self.create_error_response(str(e)) return self.create_error_response(str(e))