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

[Minor] Improve code style #2419

Merged
merged 3 commits into from
Dec 9, 2024
Merged

[Minor] Improve code style #2419

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1f801a9
improve style
merrymercy Dec 9, 2024
9a87289
improve the style
merrymercy Dec 9, 2024
f1e7c2c
fix mem style
merrymercy Dec 9, 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
1 change: 0 additions & 1 deletion python/sglang/srt/managers/detokenizer_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@
BatchStrOut,
BatchTokenIDOut,
)
from sglang.srt.managers.schedule_batch import FINISH_MATCHED_STR, FINISH_MATCHED_TOKEN
from sglang.srt.server_args import PortArgs, ServerArgs
from sglang.srt.utils import configure_logger, get_zmq_socket
from sglang.utils import find_printable_text, get_exception_traceback
Expand Down
1 change: 1 addition & 0 deletions python/sglang/srt/managers/scheduler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1198,6 +1198,7 @@ def stream_output(
decode_ids_list = []
read_offsets = []
output_ids = []

skip_special_tokens = []
spaces_between_special_tokens = []
no_stop_trim = []
Expand Down
20 changes: 10 additions & 10 deletions python/sglang/srt/managers/tokenizer_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -623,23 +623,23 @@ async def handle_loop(self):
i,
)

if not isinstance(recv_obj, BatchEmbeddingOut):
meta_info.update(
{
"completion_tokens": recv_obj.completion_tokens[i],
"cached_tokens": recv_obj.cached_tokens[i],
}
)

if isinstance(recv_obj, BatchStrOut):
out_dict = {
"text": recv_obj.output_strs[i],
"meta_info": {
**meta_info,
"completion_tokens": recv_obj.completion_tokens[i],
"cached_tokens": recv_obj.cached_tokens[i],
},
"meta_info": meta_info,
}
elif isinstance(recv_obj, BatchTokenIDOut):
out_dict = {
"token_ids": recv_obj.output_ids[i],
"meta_info": {
**meta_info,
"completion_tokens": recv_obj.completion_tokens[i],
"cached_tokens": recv_obj.cached_tokens[i],
},
"meta_info": meta_info,
}
else:
assert isinstance(recv_obj, BatchEmbeddingOut)
Expand Down
2 changes: 1 addition & 1 deletion python/sglang/srt/model_executor/model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ def __init__(
server_args.chunked_prefill_size = -1
self.mem_fraction_static *= 0.95
logger.info(
f"Automatically reduce --mem-fraction-static to {self.mem_fraction_static} "
f"Automatically reduce --mem-fraction-static to {self.mem_fraction_static:.3f} "
f"and turn off chunked prefill "
f"because this is a multimodal model."
)
Expand Down
Loading