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

[Frontend] Automatic detection of chat content format from AST (#9919)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-11-16 13:35:40 +08:00
committed by GitHub
parent 4f168f69a3
commit 32e46e000f
16 changed files with 788 additions and 350 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/entrypoints/openai/test_serving_chat.py
View File

@@ -26,7 +26,6 @@ class MockModelConfig:
tokenizer = MODEL_NAME
trust_remote_code = False
tokenizer_mode = "auto"
chat_template_text_format = "string"
max_model_len = 100
tokenizer_revision = None
multimodal_config = MultiModalConfig()
@@ -49,6 +48,7 @@ async def _async_serving_chat_init():
BASE_MODEL_PATHS,
response_role="assistant",
chat_template=CHAT_TEMPLATE,
chat_template_content_format="auto",
lora_modules=None,
prompt_adapters=None,
request_logger=None)
@@ -70,6 +70,7 @@ def test_serving_chat_should_set_correct_max_tokens():
BASE_MODEL_PATHS,
response_role="assistant",
chat_template=CHAT_TEMPLATE,
chat_template_content_format="auto",
lora_modules=None,
prompt_adapters=None,
request_logger=None)