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

2
vllm/config.py
View File

@@ -155,7 +155,6 @@ class ModelConfig:
limit_mm_per_prompt: Optional[Mapping[str, int]] = None,
use_async_output_proc: bool = True,
config_format: ConfigFormat = ConfigFormat.AUTO,
chat_template_text_format: str = "string",
hf_overrides: Optional[HfOverrides] = None,
mm_processor_kwargs: Optional[Dict[str, Any]] = None,
override_neuron_config: Optional[Dict[str, Any]] = None,
@@ -216,7 +215,6 @@ class ModelConfig:
self.model, revision)
self.dtype = _get_and_verify_dtype(self.hf_text_config, dtype)
self.use_async_output_proc = use_async_output_proc
self.chat_template_text_format = chat_template_text_format
self.mm_processor_kwargs = mm_processor_kwargs
# Set enforce_eager to False if the value is unset.