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

[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-13 21:01:39 +08:00
committed by GitHub
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/entrypoints/utils.py
View File

@@ -22,9 +22,11 @@ from vllm.entrypoints.chat_utils import (
resolve_hf_chat_template,
resolve_mistral_chat_template,
)
from vllm.entrypoints.openai.cli_args import make_arg_parser
from vllm.entrypoints.openai.protocol import (
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
)
from vllm.entrypoints.openai.cli_args import make_arg_parser
from vllm.entrypoints.openai.engine.protocol import (
CompletionRequest,
StreamOptions,
)