biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Update batch invariant to use attention config (#30704)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Matthew Bonanni
2025-12-15 15:24:16 -05:00
committed by GitHub
parent a450c64a30
commit 60dbf7d8f1
2 changed files with 24 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/v1/worker/gpu_worker.py
View File

@@ -931,10 +931,11 @@ def init_worker_distributed_environment(
backend: str = "nccl",
) -> None:
"""Initialize the distributed environment."""
attention_config = vllm_config.attention_config
parallel_config = vllm_config.parallel_config
from vllm.model_executor.layers.batch_invariant import init_batch_invariance
init_batch_invariance()
init_batch_invariance(attention_config.backend)
set_custom_all_reduce(not parallel_config.disable_custom_all_reduce)
init_method = distributed_init_method or "env://"