[perf] Minicpm o4.5 optimization (#5228)

Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Co-authored-by: Sy03 <1370724210@qq.com>
This commit is contained in:
rein yangandSy03 authored and GitHub committed 2026-07-24 17:20:39 +08:00
1 parent acf941da4d
commit ad3a162eb8
54 files changed
+3861 -3997

No files matched your search

@@ -36,6 +36,7 @@ from vllm.v1.worker.gpu_model_runner import (
from vllm.v1.worker.ubatch_utils import maybe_create_ubatch_slices
from vllm.v1.worker.utils import sanity_check_mm_encoder_outputs
from vllm_omni.distributed.omni_connectors.utils.config import get_stage_connector_role
from vllm_omni.outputs import OmniModelRunnerOutput
from vllm_omni.utils.mm_outputs import partition_payload_list
from vllm_omni.worker.gpu_ar_model_runner import ExecuteModelState, _ensure_tensor_values
@@ -68,7 +69,10 @@ class GPUGenerationModelRunner(OmniGPUModelRunner, OmniConnectorModelRunnerMixin
"DyninOmniForConditionalGeneration",
"IndexTTS2S2MelDecoder",
}
if getattr(self.model_config, "model_arch", None) in _OMNI_CONNECTOR_INIT_ARCHS:
if (
getattr(self.model_config, "model_arch", None) in _OMNI_CONNECTOR_INIT_ARCHS
or get_stage_connector_role(self.model_config) is not None
):
self.init_omni_connectors(
model_config=self.model_config,
)
@@ -317,6 +321,8 @@ class GPUGenerationModelRunner(OmniGPUModelRunner, OmniConnectorModelRunnerMixin
)
# [Omni] Pass token counts per request for code2wav output slicing
model_kwargs["seq_token_counts"] = tokens
if getattr(self.model, "requires_request_ids", False):
model_kwargs["request_ids"] = list(req_ids)
# Set cudagraph mode to none if calc_kv_scales is true.
# KV scales calculation involves dynamic operations that are incompatible