[Misc] Add cProfile helpers (#15074)

Signed-off-by: Russell Bryant <rbryant@redhat.com>
This commit is contained in:
Russell Bryant 2025-03-21 07:56:09 -04:00 committed by GitHub
parent 8afcd0f633
commit 61e8c18350
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 97 additions and 0 deletions

View File

@ -124,3 +124,52 @@ nsys stats report1.nsys-rep
GUI example:
<img width="1799" alt="Screenshot 2025-03-05 at 11 48 42AM" src="https://github.com/user-attachments/assets/c7cff1ae-6d6f-477d-a342-bd13c4fc424c" />
## Profiling vLLM Python Code
The Python standard library includes
[cProfile](https://docs.python.org/3/library/profile.html) for profiling Python
code. vLLM includes a couple of helpers that make it easy to apply it to a section of vLLM.
Both the `vllm.utils.cprofile` and `vllm.utils.cprofile_context` functions can be
used to profile a section of code.
### Example usage - decorator
The first helper is a Python decorator that can be used to profile a function.
If a filename is specified, the profile will be saved to that file. If no filename is
specified, profile data will be printed to stdout.
```python
import vllm.utils
@vllm.utils.cprofile("expensive_function.prof")
def expensive_function():
# some expensive code
pass
```
### Example Usage - context manager
The second helper is a context manager that can be used to profile a block of
code. Similar to the decorator, the filename is optional.
```python
import vllm.utils
def another_function():
# more expensive code
pass
with vllm.utils.cprofile_context("another_function.prof"):
another_function()
```
### Analyzing Profile Results
There are multiple tools available that can help analyze the profile results.
One example is [snakeviz](https://jiffyclub.github.io/snakeviz/).
```bash
pip install snakeviz
snakeviz expensive_function.prof
```

View File

@ -2405,3 +2405,51 @@ def swap_dict_values(obj: dict[_K, _V], key1: _K, key2: _K) -> None:
obj[key1] = v2
else:
obj.pop(key1, None)
@contextlib.contextmanager
def cprofile_context(save_file: Optional[str] = None):
"""Run a cprofile
Args:
save_file: path to save the profile result. "1" or
None will result in printing to stdout.
"""
import cProfile
prof = cProfile.Profile()
prof.enable()
try:
yield
finally:
prof.disable()
if save_file and save_file != "1":
prof.dump_stats(save_file)
else:
prof.print_stats(sort="cumtime")
def cprofile(save_file: Optional[str] = None, enabled: bool = True):
"""Decorator to profile a Python method using cProfile.
Args:
save_file: Path to save the profile result.
If "1", None, or "", results will be printed to stdout.
enabled: Set to false to turn this into a no-op
"""
def decorator(func: Callable):
@wraps(func)
def wrapper(*args, **kwargs):
if not enabled:
# If profiling is disabled, just call the function directly.
return func(*args, **kwargs)
with cprofile_context(save_file):
return func(*args, **kwargs)
return wrapper
return decorator