Skip to content

Commit 22ab0f9

Browse files
format
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
1 parent 90c7c8b commit 22ab0f9

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

vllm/v1/worker/gpu_model_runner.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2618,8 +2618,8 @@ def _determine_batch_execution_and_padding(
26182618
ubatch_slices, num_tokens_across_dp = None, None
26192619
if self.vllm_config.parallel_config.data_parallel_size > 1:
26202620
# Disable DP padding when running eager to avoid excessive padding when
2621-
# running prefills. This lets us set cudagraph_mode="NONE" on the prefiller in
2622-
# a P/D setup and still use CUDA graphs (enabled by this padding) on the
2621+
# running prefills. This lets us set cudagraph_mode="NONE" on the prefiller
2622+
# in a P/D setup and still use CUDA graphs (enabled by this padding) on the
26232623
# decoder.
26242624
allow_dp_padding = (
26252625
self.compilation_config.cudagraph_mode != CUDAGraphMode.NONE

0 commit comments

Comments
 (0)