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

[V0 Deprecation] Remove Prompt Adapters (#20588)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-07-23 19:36:48 -04:00
committed by GitHub
parent 78c13e30e1
commit 82ec66f514
60 changed files with 126 additions and 1727 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/entrypoints/openai/serving_pooling.py
View File

@@ -94,17 +94,10 @@ class OpenAIServingPooling(OpenAIServing):
try:
truncate_prompt_tokens = _validate_truncation_size(
self.max_model_len, truncate_prompt_tokens)
(
lora_request,
prompt_adapter_request,
) = self._maybe_get_adapters(request)
lora_request = self._maybe_get_adapters(request)
tokenizer = await self.engine_client.get_tokenizer(lora_request)
if prompt_adapter_request is not None:
raise NotImplementedError("Prompt adapter is not supported "
"for pooling models")
if isinstance(request, PoolingChatRequest):
(
_,
@@ -153,8 +146,7 @@ class OpenAIServingPooling(OpenAIServing):
self._log_inputs(request_id_item,
request_prompts[i],
params=pooling_params,
lora_request=lora_request,
prompt_adapter_request=prompt_adapter_request)
lora_request=lora_request)
trace_headers = (None if raw_request is None else await
self._get_trace_headers(raw_request.headers))