Skip to content

Add DeepSeek persistent L3 profiling #111

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
superxf merged 1 commit into from
Jul 24, 2026
Merged

Add DeepSeek persistent L3 profiling #111

Show file tree
Hide file tree
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
4 changes: 3 additions & 1 deletion pypto_serving/model/deepseek/npu_executor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,7 @@
DEEPSEEK_V4_HCA_NUM_LAYERS,
)
from pypto_serving.model.deepseek.weight_loader import DeepSeekV4WeightStore
from pypto_serving.tools.profile import profile_span


_AST_INT_OPERATORS = {
Expand Down Expand Up @@ -550,7 +551,8 @@ def _compile_l3_callable(self, name: str, jit_fn: object, dummy_args: Sequence[A
enable_scope_stats=True,
distributed_config=distributed_config,
)
compiled = jit_fn.compile(*dummy_args, config=run_config)
with profile_span(f"DeepSeekV4PyptoExecutor.compile.{name}", cat="executor"):
compiled = jit_fn.compile(*dummy_args, config=run_config)
if not isinstance(compiled, DistributedCompiledProgram):
raise TypeError(f"{name} did not compile to DistributedCompiledProgram; got {type(compiled).__name__}")
return DeepSeekV4L3Callable(compiled=compiled, name=name)
Expand Down
Loading
Loading