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

[BugFix] Prevent LLM.encode for non-generation Models (#5184)

Browse Source 
Co-authored-by: mgoin <michael@neuralmagic.com>
This commit is contained in:
Robert Shaw 2024-06-01 19:35:41 -04:00 committed by GitHub
parent c2d6d2f960
commit 044793d8df
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/entrypoints/llm.py
View File

@ -276,6 +276,11 @@ class LLM:
considered legacy and may be deprecated in the future. You should considered legacy and may be deprecated in the future. You should
instead pass them via the ``inputs`` parameter. instead pass them via the ``inputs`` parameter.
""" """
if self.llm_engine.model_config.embedding_mode:
raise ValueError(
"LLM.generate() is only supported for generation models "
"(XForCausalLM).")
if prompt_token_ids is not None or multi_modal_data is not None: if prompt_token_ids is not None or multi_modal_data is not None:
inputs = self._convert_v1_inputs( inputs = self._convert_v1_inputs(
prompts=cast(Optional[Union[str, List[str]]], prompts), prompts=cast(Optional[Union[str, List[str]]], prompts),
@ -420,6 +425,11 @@ class LLM:
considered legacy and may be deprecated in the future. You should considered legacy and may be deprecated in the future. You should
instead pass them via the ``inputs`` parameter. instead pass them via the ``inputs`` parameter.
""" """
if not self.llm_engine.model_config.embedding_mode:
raise ValueError(
"LLM.encode() is only supported for embedding models (XModel)."
)
if prompt_token_ids is not None or multi_modal_data is not None: if prompt_token_ids is not None or multi_modal_data is not None:
inputs = self._convert_v1_inputs( inputs = self._convert_v1_inputs(
prompts=cast(Optional[Union[str, List[str]]], prompts), prompts=cast(Optional[Union[str, List[str]]], prompts),