Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion vllm/executor/executor_base.py
Original file line number Diff line number Diff line change
Expand Up @@ -109,7 +109,7 @@ def initialize_cache(self, num_gpu_blocks: int, num_cpu_blocks) -> None:
"""
# NOTE: This is logged in the executor because there can be >1 workers.
logger.info("# %s blocks: %d, # CPU blocks: %d",
vllm.platforms.current_platform.dispatch_key,
vllm.platforms.current_platform.device_name,
num_gpu_blocks, num_cpu_blocks)
max_concurrency = (num_gpu_blocks * self.cache_config.block_size /
self.model_config.max_model_len)
Expand Down
2 changes: 1 addition & 1 deletion vllm/platforms/interface.py
Original file line number Diff line number Diff line change
Expand Up @@ -327,7 +327,7 @@ def get_device_communicator_cls(cls) -> str:
"""
Get device specific communicator class for distributed communication.
"""
return "vllm.distributed.device_communicator.base_device_communicator.DeviceCommunicatorBase" # noqa
return "vllm.distributed.device_communicators.base_device_communicator.DeviceCommunicatorBase" # noqa


class UnspecifiedPlatform(Platform):
Expand Down