Process-Scoped GPU Memory Accounting (#1204)

Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
This commit is contained in:
dsinghvi authored and GitHub committed 2026-02-08 22:43:02 +08:00
1 parent 01e0a8f284
commit 59024bee62
6 files changed
+563 -338

No files matched your search

+2 -2
View File
@@ -7,18 +7,18 @@ from vllm.platforms import current_platform
from vllm.utils.mem_utils import MemorySnapshot, format_gib
from vllm.utils.torch_utils import set_random_seed
from vllm.v1.utils import report_usage_stats
from vllm.v1.worker.gpu_worker import Worker as GPUWorker
from vllm.v1.worker.gpu_worker import init_worker_distributed_environment
from vllm.v1.worker.utils import request_memory
from vllm.v1.worker.workspace import init_workspace_manager
from vllm_omni.worker.base import OmniGPUWorkerBase
from vllm_omni.worker.gpu_generation_model_runner import GPUGenerationModelRunner
from vllm_omni.worker.mixins import OmniWorkerMixin
logger = init_logger(__name__)
class GPUGenerationWorker(OmniWorkerMixin, GPUWorker):
class GPUGenerationWorker(OmniWorkerMixin, OmniGPUWorkerBase):
"""GPU Worker for Generation model (non-autoregressive waveform generation).
Usage in stage config: