Skip to content

fix gpu_id_step #7384

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

Open
TomQuartz wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix gpu_id_step #7384

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
52794ef
fix gpu_id_step
TomQuartz Jun 20, 2025
76c8b1a
Merge branch 'main' into fix/gpu-id-step
TomQuartz Jun 20, 2025
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
9 changes: 4 additions & 5 deletions python/sglang/srt/entrypoints/engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,7 +263,7 @@ async def async_generate(
raise ValueError("data_parallel_rank must be non-negative")
elif data_parallel_rank >= self.server_args.dp_size:
raise ValueError(
f"data_parallel_rank must be in range [0, {self.server_args.dp_size-1}]"
f"data_parallel_rank must be in range [0, {self.server_args.dp_size - 1}]"
)

logger.info(f"data_parallel_rank: {data_parallel_rank}")
Expand Down Expand Up @@ -689,11 +689,10 @@ def _launch_subprocesses(
for pp_rank in pp_rank_range:
for tp_rank in tp_rank_range:
reader, writer = mp.Pipe(duplex=False)
gpu_id = (
server_args.base_gpu_id
+ ((pp_rank % pp_size_per_node) * tp_size_per_node)
+ (tp_rank % tp_size_per_node) * server_args.gpu_id_step
gpu_offset = (pp_rank % pp_size_per_node) * tp_size_per_node + (
tp_rank % tp_size_per_node
)
gpu_id = server_args.base_gpu_id + gpu_offset * server_args.gpu_id_step
proc = mp.Process(
target=run_scheduler_process,
args=(
Expand Down