biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Truncation control for embedding models (#14776)

Browse Source 
Signed-off-by: Gabriel Marinho <gmarinho@ibm.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
This commit is contained in:
Gabriel Marinho
2025-04-29 22:24:57 -03:00
committed by GitHub
parent 4055130a85
commit 1c2bc7ead0
21 changed files with 333 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/engine/llm_engine.py
View File

@@ -645,6 +645,7 @@ class LLMEngine:
params: Union[SamplingParams, PoolingParams],
arrival_time: Optional[float] = None,
lora_request: Optional[LoRARequest] = None,
tokenization_kwargs: Optional[dict[str, Any]] = None,
trace_headers: Optional[Mapping[str, str]] = None,
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
priority: int = 0,
@@ -678,6 +679,7 @@ class LLMEngine:
params: Optional[Union[SamplingParams, PoolingParams]] = None,
arrival_time: Optional[float] = None,
lora_request: Optional[LoRARequest] = None,
tokenization_kwargs: Optional[dict[str, Any]] = None,
trace_headers: Optional[Mapping[str, str]] = None,
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
priority: int = 0,
@@ -758,6 +760,7 @@ class LLMEngine:
processed_inputs = self.input_preprocessor.preprocess(
prompt,
tokenization_kwargs=tokenization_kwargs,
lora_request=lora_request,
prompt_adapter_request=prompt_adapter_request,
)