[Model Runner V2] Add ModelStateInterface [4/N] (#35621)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
This commit is contained in:
Woosuk Kwon
2026-02-28 13:19:45 -08:00
committed by GitHub
parent 95a395dbec
commit e3eb146f7a
5 changed files with 90 additions and 4 deletions
+2 -2
View File
@@ -78,7 +78,7 @@ from vllm.v1.worker.gpu.kv_connector import (
)
from vllm.v1.worker.gpu.lora_utils import LoraState
from vllm.v1.worker.gpu.mm.encoder_cache import EncoderCache
from vllm.v1.worker.gpu.model_states import ModelState
from vllm.v1.worker.gpu.model_states import init_model_state
from vllm.v1.worker.gpu.pool.pooling_runner import PoolingRunner
from vllm.v1.worker.gpu.pp_utils import pp_broadcast, pp_receive
from vllm.v1.worker.gpu.sample.output import SamplerOutput
@@ -267,7 +267,7 @@ class GPUModelRunner(LoRAModelRunnerMixin):
prepare_communication_buffer_for_model(self.speculator)
# Initialize the components that require the model.
self.model_state = ModelState(
self.model_state = init_model_state(
self.vllm_config, self.model, self.encoder_cache, self.device
)
if self.is_pooling_model: