Merged
Conversation
Merged
…remove unused code
…remove unused code
…and refine output validation
…bility, and format code for consistency
johnnynunez
requested review from
BBuf,
FlamingoPg,
HaiShaw,
ispobock,
merrymercy,
yizhang2077 and
zhyncs
as code owners
johnnynunez
changed the title
ishandhanani
changed the title
Contributor
Author
Seems the test itself |
Contributor
Author
unit test fixed |
4 tasks
Collaborator
|
Result of /usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
import pynvml # type: ignore[import]
============================= test session starts ==============================
platform linux -- Python 3.12.11, pytest-8.4.2, pluggy-1.6.0
rootdir: /sgl-workspace/sglang/sgl-kernel
configfile: pyproject.toml
plugins: typeguard-4.4.4, anyio-4.11.0
collected 1968 items
sgl-kernel/tests/test_flash_attention_4.py ............................. [ 1%]
........................................................................ [ 5%]
........................................................................ [ 8%]
.........................ssssssssssssssssss......ssssssssssssssssss..... [ 12%]
.ssssssssssssssssss......ssssssssssssssssss............................. [ 16%]
........................................................................ [ 19%]
........................................................................ [ 23%]
........................................................................ [ 27%]
.................................................ssssssssssssssssss..... [ 30%]
.ssssssssssssssssss......ssssssssssssssssss......ssssssssssssssssss..... [ 34%]
.ssssssssssssssssss......ssssssssssssssssss............................. [ 38%]
........................................................................ [ 41%]
.ssssssssssssssssss......ssssssssssssssssss............................. [ 45%]
........................................................................ [ 49%]
........................................................................ [ 52%]
........................................................................ [ 56%]
........................................................................ [ 60%]
........................................................................ [ 63%]
........................................................................ [ 67%]
........................................................................ [ 70%]
........................................................................ [ 74%]
........................................................................ [ 78%]
........................................................................ [ 81%]
........................................................................ [ 85%]
........................................................................ [ 89%]
.......................................................ssssssssssss..... [ 92%]
...............................ssssssssssss............................. [ 96%]
.......ssssssssssss....................................ssssssssssss [100%]
=============================== warnings summary ===============================
tests/test_flash_attention_4.py: 51414 warnings
/usr/local/lib/python3.12/dist-packages/nvidia_cutlass_dsl/python_packages/cutlass/base_dsl/_mlir_helpers/op.py:31: DeprecationWarning: cute.arch.exp2 is deprecated, use cute.math.exp2 with `fastmath=True` instead
res_or_list = opFunc(*args, **kwargs, loc=loc)
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
======== 1704 passed, 264 skipped, 51414 warnings in 713.71s (0:11:53) ========= |
Collaborator
|
Result of ...
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 64.57it/s]
Accuracy: 0.730
Invalid: 0.010
Latency: 1.587 s
Output throughput: 4754.717 token/s
{'accuracy': np.float64(0.73), 'invalid': np.float64(0.01), 'latency': 1.587055522017181, 'output_throughput': 4754.717081610904}
.
----------------------------------------------------------------------
Ran 1 test in 62.719s
OK
|
Contributor
Author
|
@zhyncs @Fridge003 is this ready to merge now? |
zhyncs
reviewed
Oct 19, 2025
| TestFile("test_disaggregation_pp.py", 140), | ||
| ], | ||
| "per-commit-4-gpu-b200": [ | ||
| # TestFile("test_flash_attention_4.py"), |
Collaborator
There was a problem hiding this comment.
we should enable the fa4 unit test on b200
Collaborator
There was a problem hiding this comment.
We can add it back after sgl-kernel bumps.
This test can pass locally #11606 (comment)
Collaborator
There was a problem hiding this comment.
ok Can you help me look into this issue https://github.com/sgl-project/sglang/actions/runs/18628168698/job/53126330363?pr=11606
zhyncs
approved these changes
Oct 20, 2025
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Motivation
Fix FA3/FA4 with latest changes