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

Fix SchedulerConfig params #459

Merged
merged 2 commits into from
Nov 5, 2024
Merged

Fix SchedulerConfig params #459

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8500d8d
Fix SchedulerConfig params
ldurejko Nov 5, 2024
6ac0442
adapt SchedulerConfig docstring
ldurejko Nov 5, 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
8 changes: 4 additions & 4 deletions vllm/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -940,9 +940,6 @@ class SchedulerConfig:
a single iteration.
max_num_seqs: Maximum number of sequences to be processed in a single
iteration.
max_num_prefill_seqs: Maximum number of prefill sequences to be
processed in a single iteration. Used only with padding-aware
scheduling.
max_model_len: Maximum length of a sequence (including prompt
and generated text).
use_v2_block_manager: Whether to use the BlockSpaceManagerV2 or not.
Expand All @@ -966,14 +963,16 @@ class SchedulerConfig:
when SPMD worker architecture is enabled. I.e.,
VLLM_USE_RAY_SPMD_WORKER=1
policy: The scheduling policy to use. "fcfs" (default) or "priority".
max_num_prefill_seqs: Maximum number of prefill sequences to be
processed in a single iteration. Used only with padding-aware
scheduling.
use_padding_aware_scheduling: If True, scheduler will consider padded
tokens in prefill.
"""

def __init__(self,
max_num_batched_tokens: Optional[int],
max_num_seqs: int,
max_num_prefill_seqs: Optional[int],
max_model_len: int,
use_v2_block_manager: bool = True,
num_lookahead_slots: int = 0,
Expand All @@ -986,6 +985,7 @@ def __init__(self,
multi_step_stream_outputs: bool = False,
send_delta_data: bool = False,
policy: str = "fcfs",
max_num_prefill_seqs: Optional[int] = None,
use_padding_aware_scheduling=False) -> None:
if max_num_batched_tokens is None:
if enable_chunked_prefill:
Expand Down
Loading