Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 2 additions & 0 deletions slime/backends/megatron_utils/model_provider.py
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,8 @@ def __init__(
self.sequence_parallel = config.sequence_parallel
if self.sequence_parallel:
self.weight.sequence_parallel = True
if bias:
self.bias.sequence_parallel = True

self.weight.data.normal_(mean=0.0, std=0.02)
if bias:
Expand Down
1 change: 1 addition & 0 deletions slime/backends/sglang_utils/arguments.py
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@ def add_sglang_arguments(parser):
Add arguments to the parser for the SGLang server.
"""
parser = add_sglang_router_arguments(parser)
parser.set_defaults(router_balance_abs_threshold=10, router_balance_rel_threshold=1.2)
parser.add_argument("--sglang-server-concurrency", type=int, default=512)

old_add_argument = parser.add_argument
Expand Down