[Docs] Add example for Renderer.render_cmpl() usage (#54265)
Signed-off-by: null-Exception1 <rising1legend@gmail.com>
This commit is contained in:
@@ -652,6 +652,17 @@ class AsyncLLM(EngineClient):
|
|||||||
|
|
||||||
The caller of generate() iterates the returned AsyncGenerator,
|
The caller of generate() iterates the returned AsyncGenerator,
|
||||||
returning the RequestOutput back to the caller.
|
returning the RequestOutput back to the caller.
|
||||||
|
|
||||||
|
Note:
|
||||||
|
Passing a raw prompt string directly to this method is deprecated.
|
||||||
|
Advanced power-users can manually bypass the raw-prompt fallback
|
||||||
|
path using the Engine's underlying Renderer pipeline:
|
||||||
|
|
||||||
|
>>> from vllm.inputs import parse_model_prompt
|
||||||
|
>>> parsed = parse_model_prompt(self.model_config, "Prompt text")
|
||||||
|
>>> params = self.renderer.default_cmpl_tok_params
|
||||||
|
>>> (engine_input,) = self.renderer.render_cmpl([parsed], params)
|
||||||
|
>>> gen = self.generate(engine_input, sampling_params, request_id)
|
||||||
"""
|
"""
|
||||||
|
|
||||||
q: RequestOutputCollector | None = None
|
q: RequestOutputCollector | None = None
|
||||||
|
|||||||
Reference in New Issue
Block a user