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

11
vllm/entrypoints/openai/serving_chat.py
View File

@@ -147,11 +147,8 @@ class OpenAIServingChat(OpenAIServing):
raise self.engine_client.dead_error
try:
(
lora_request,
prompt_adapter_request,
) = self._maybe_get_adapters(request,
supports_default_mm_loras=True)
lora_request = self._maybe_get_adapters(
request, supports_default_mm_loras=True)
model_name = self._get_model_name(request.model, lora_request)
@@ -239,8 +236,7 @@ class OpenAIServingChat(OpenAIServing):
self._log_inputs(request_id,
request_prompts[i],
params=sampling_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))
@@ -259,7 +255,6 @@ class OpenAIServingChat(OpenAIServing):
request_id,
lora_request=lora_request,
trace_headers=trace_headers,
prompt_adapter_request=prompt_adapter_request,
priority=request.priority,
)