Skip to content

[User Experience] Remove nvprof_nvtx_pop() in gemm.py #74309

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
merged 3 commits into from
Aug 1, 2025
Merged

[User Experience] Remove nvprof_nvtx_pop() in gemm.py #74309

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
e0c8af1
fix(gemm.py): delete nvprof_nvtx_pop()
hushenwei2000 Jul 29, 2025
e3e99ac
Merge branch 'PaddlePaddle:develop' into fix_remove_nvprof_nvtx_pop
hushenwei2000 Jul 30, 2025
e8dc443
fix(compiler.py): delete nvprof_nvtx_pop()
hushenwei2000 Jul 30, 2025
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
3 changes: 0 additions & 3 deletions python/paddle/incubate/fp8/deep_gemm/jit/compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,6 @@
import subprocess
import uuid

import paddle

from ..utils import get_cuda_home
from . import interleave_ffma
from .runtime import Runtime, RuntimeCache
Expand Down Expand Up @@ -158,7 +156,6 @@ def build(name: str, arg_defs: tuple, code: str) -> Runtime:
if os.getenv("DG_JIT_DEBUG", None):
print(f"Using cached JIT runtime {name} during build")
return runtime_cache[path]
paddle.base.core.nvprof_nvtx_pop()
# Write the code
os.makedirs(path, exist_ok=True)
args_path = f"{path}/kernel.args"
Expand Down
2 changes: 0 additions & 2 deletions python/paddle/incubate/fp8/deep_gemm/jit_kernels/gemm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -255,7 +255,6 @@ def gemm_fp8_fp8_bf16_nt(
# NOTES: `get_tma_aligned_lhs_scales` may launch a kernel if not processed by previous kernels
lhs_scales = get_col_major_tma_aligned_tensor(lhs_scales)
assert rhs_scales.is_contiguous()
paddle.base.core.nvprof_nvtx_pop()

# Do nothing if `m` is zero
if m == 0:
Expand All @@ -275,4 +274,3 @@ def gemm_fp8_fp8_bf16_nt(

# Run the kernel.
runtime(*args)
paddle.base.core.nvprof_nvtx_pop()