chat_template_kwargs
A parameter in vLLM used to pass extra variables to a Jinja chat template; the enable_thinking switch can be used to control whether thinking content is generated.
Timeline (last 90 days)
On the vLLM endpoint, disabling thinking via chat_template_kwargs: { enable_thinking: false } took 65 seconds, whereas sending reasoning_effort none took 2 seconds.
The endpoint adaptation strategy that ultimately emerged is: send reasoning_effort: 'none' to standard endpoints; for vLLM, switch to chat_template_kwargs after the value is rejected; and for relay endpoints that return empty streaming responses, send no reasoning parameters at all.
All Facts (2)
On the vLLM endpoint, disabling thinking via chat_template_kwargs: { enable_thinking: false } took 65 seconds, whereas sending reasoning_effort none took 2 seconds.
50%UnverifiedThe endpoint adaptation strategy that ultimately emerged is: send reasoning_effort: 'none' to standard endpoints; for vLLM, switch to chat_template_kwargs after the value is rejected; and for relay endpoints that return empty streaming responses, send no reasoning parameters at all.
50%