Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Enable padding aware scheduling by default on HPU #606

Merged
merged 3 commits into from
Dec 10, 2024
+2 −2
Merged

Enable padding aware scheduling by default on HPU #606

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0272ab6
Enable padding aware scheduling by default
kzawora-intel Dec 10, 2024
57c16cc
Enable padding aware scheduling by default on HPU
kzawora-intel Dec 10, 2024
72cc909
ruff stuff
kzawora-intel Dec 10, 2024
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
4 changes: 2 additions & 2 deletions vllm/engine/arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@ class EngineArgs:
enable_prefix_caching: Optional[bool] = None
disable_sliding_window: bool = False
use_v2_block_manager: bool = True
use_padding_aware_scheduling: bool = False
use_padding_aware_scheduling: bool = current_platform.is_hpu()
swap_space: float = 4 # GiB
cpu_offload_gb: float = 0 # GiB
gpu_memory_utilization: float = 0.90
Expand Down Expand Up @@ -454,7 +454,7 @@ def add_cli_args(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
action='store_true',
help=('Use padding-aware scheduling. If True, the scheduler '
'will consider padded tokens in prefill. '
'By default this is set to False. '))
'By default this is set to False on non-HPU devices. '))
parser.add_argument(
'--num-lookahead-slots',
type=int,
Expand Down
Loading