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

[Refactor] [10/N] to simplify the vLLM openai completion serving architecture (#32369)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-15 15:41:34 +08:00
committed by GitHub
parent ae1eba6a9a
commit 4c1c501a7e
43 changed files with 777 additions and 642 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/entrypoints/openai/chat_completion/serving.py
View File

@@ -54,6 +54,7 @@ from vllm.entrypoints.openai.engine.serving import (
OpenAIServing,
clamp_prompt_logprobs,
)
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.openai.parser.harmony_utils import (
get_developer_message,
get_stop_tokens_for_assistant_actions,
@@ -63,7 +64,6 @@ from vllm.entrypoints.openai.parser.harmony_utils import (
parse_chat_output,
render_for_completion,
)
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.entrypoints.openai.utils import maybe_filter_parallel_tool_calls
from vllm.entrypoints.utils import get_max_tokens, should_include_usage
from vllm.inputs.data import TokensPrompt