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

4
vllm/v1/engine/llm_engine.py
View File

@@ -175,6 +175,7 @@ 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,
@@ -182,7 +183,8 @@ class LLMEngine:
# Process raw inputs into the request.
prompt_str, request = self.processor.process_inputs(
request_id, prompt, params, arrival_time, lora_request,
trace_headers, prompt_adapter_request, priority)
tokenization_kwargs, trace_headers, prompt_adapter_request,
priority)
n = params.n if isinstance(params, SamplingParams) else 1