[Frontend] Introduce Renderer for processing chat messages (using ModelConfig) (#30200)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -21,9 +21,10 @@ from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
|
||||
from vllm.outputs import PoolingRequestOutput, RequestOutput
|
||||
from vllm.plugins.io_processors import get_io_processor
|
||||
from vllm.pooling_params import PoolingParams
|
||||
from vllm.renderers import RendererLike
|
||||
from vllm.sampling_params import SamplingParams
|
||||
from vllm.tasks import SupportedTask
|
||||
from vllm.tokenizers import TokenizerLike, cached_tokenizer_from_config
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.tracing import init_tracer
|
||||
from vllm.usage.usage_lib import UsageContext
|
||||
from vllm.v1.engine import EngineCoreRequest
|
||||
@@ -84,9 +85,7 @@ class LLMEngine:
|
||||
self.dp_group = None
|
||||
self.should_execute_dummy_batch = False
|
||||
|
||||
tokenizer = cached_tokenizer_from_config(self.model_config)
|
||||
|
||||
self.input_processor = InputProcessor(self.vllm_config, tokenizer)
|
||||
self.input_processor = InputProcessor(self.vllm_config)
|
||||
self.io_processor = get_io_processor(
|
||||
self.vllm_config,
|
||||
self.model_config.io_processor_plugin,
|
||||
@@ -357,12 +356,11 @@ class LLMEngine:
|
||||
return self.input_processor.tokenizer
|
||||
|
||||
def get_tokenizer(self) -> TokenizerLike:
|
||||
if self.tokenizer is None:
|
||||
raise ValueError(
|
||||
"Unable to get tokenizer because `skip_tokenizer_init=True`"
|
||||
)
|
||||
return self.input_processor.get_tokenizer()
|
||||
|
||||
return self.tokenizer
|
||||
@property
|
||||
def renderer(self) -> RendererLike:
|
||||
return self.input_processor.renderer
|
||||
|
||||
def do_log_stats(self) -> None:
|
||||
"""Log stats if logging is enabled."""
|
||||
|
||||
Reference in New Issue
Block a user