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

[Renderer] Consolidate factory methods (#38218)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-03-26 20:19:22 +08:00
committed by GitHub
parent 757eafcf37
commit 2e225f7bd2
16 changed files with 32 additions and 232 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/entrypoints/openai/chat_completion/test_chat_error.py
View File

@@ -16,7 +16,7 @@ from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.render.serving import OpenAIServingRender
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.renderers.hf import HfRenderer
from vllm.tokenizers.registry import tokenizer_args_from_config
from vllm.tokenizers.registry import cached_tokenizer_from_config
from vllm.v1.engine.async_llm import AsyncLLM
MODEL_NAME = "openai-community/gpt2"
@@ -72,11 +72,9 @@ class MockVllmConfig:
def _build_renderer(model_config: MockModelConfig):
_, tokenizer_name, _, kwargs = tokenizer_args_from_config(model_config)
return HfRenderer.from_config(
return HfRenderer(
MockVllmConfig(model_config, parallel_config=MockParallelConfig()),
tokenizer_kwargs={**kwargs, "tokenizer_name": tokenizer_name},
cached_tokenizer_from_config(model_config),
)