implementation detail · filed under software implementation
vLLM language-model-only mode
A vLLM serving mode that skips the vision encoder.
Also called --language-model-only.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- optional
How sources treat it
One count per evidence span, weakest treatment to strongest.
optional 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
--language-model-only
optionalinference servingin Qwen3.5-397B-A17BQwen
Filed alongside
Other methods under software implementation :: inference engine.