anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[core]refactor communication layer: PR1(Added Refactor Infra Only) (#1555)

Browse Source 
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
NATUREandHongsheng Liu authored and GitHub committed 2026-04-13 16:01:14 +08:00
1 parent 2b70e89535
commit 0d4e975e1b
9 files changed
+4712 -3
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/worker/gpu_generation_model_runner.py
+2 -1
View File
@@ -39,11 +39,12 @@ from vllm.v1.worker.utils import sanity_check_mm_encoder_outputs
from vllm_omni.outputs import OmniModelRunnerOutput
from vllm_omni.worker.gpu_ar_model_runner import ExecuteModelState
from vllm_omni.worker.gpu_model_runner import OmniGPUModelRunner
from vllm_omni.worker.omni_connector_model_runner_mixin import OmniConnectorModelRunnerMixin
logger = logging.getLogger(__name__)
class GPUGenerationModelRunner(OmniGPUModelRunner):
class GPUGenerationModelRunner(OmniGPUModelRunner, OmniConnectorModelRunnerMixin):
"""Generation model runner for vLLM-Omni (non-autoregressive).
- Reuses GPUModelRunner preparation, multimodal handling, and TP/PP/DP glue.