Skip to content

Cache _load_architecture by model_type #36

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

Merged
YWHyuk merged 1 commit into from
May 19, 2026
Merged

Cache _load_architecture by model_type #36

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 7 additions & 0 deletions serving/core/trace_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,10 @@
# ----------------------------------------------------------------------
_perf_db_cache = {}

# key: model_type
# value: parsed architecture yaml dict
_arch_cache = {}

logger = get_logger("TraceGenerator")


Expand Down Expand Up @@ -245,6 +249,8 @@ def flush(self, ctx, enable_attn_offloading=False):

def _load_architecture(model_type):
"""Load catalog + sequence from profiler/models/<model_type>.yaml."""
if model_type in _arch_cache:
return _arch_cache[model_type]
path = _arch_yaml_path(model_type)
if not os.path.isfile(path):
raise FileNotFoundError(
Expand All @@ -257,6 +263,7 @@ def _load_architecture(model_type):
raise KeyError(
f"Architecture yaml {path} must define both 'catalog' and 'sequence'."
)
_arch_cache[model_type] = arch
return arch


Expand Down
Loading