Skip to content

chore: bump sgl-kernel version to 0.4.1.post1 #23720

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
Kangyan-Zhou merged 2 commits into from
Apr 26, 2026
Merged

chore: bump sgl-kernel version to 0.4.1.post1 #23720

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0abab4a
chore: bump sgl-kernel version to 0.4.1.post1
sglang-bot Apr 25, 2026
0c723b1
[CI] temporarily skip test_nvidia_nemotron_3_nano
kzhou-radixark Apr 25, 2026
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
2 changes: 1 addition & 1 deletion sgl-kernel/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ build-backend = "scikit_build_core.build"

[project]
name = "sglang-kernel"
version = "0.4.1"
version = "0.4.1.post1"
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Apr 25, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

The version bump to 0.4.1.post1 should also be reflected in the main python/pyproject.toml file, which currently pins sglang-kernel==0.4.1 at line 62. Updating this dependency is necessary for the main package to utilize the new kernel version.

authors = [
{ name="SGLang Kernel Team", email="sglang@lmsys.org" },
]
Expand Down
2 changes: 1 addition & 1 deletion sgl-kernel/pyproject_cpu.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ build-backend = "scikit_build_core.build"

[project]
name = "sglang-kernel-cpu"
version = "0.4.1"
version = "0.4.1.post1"
description = "Kernel Library for SGLang"
readme = "README.md"
requires-python = ">=3.10"
Expand Down
2 changes: 1 addition & 1 deletion sgl-kernel/pyproject_musa.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ build-backend = "setuptools.build_meta"

[project]
name = "sglang-kernel"
version = "0.4.1"
version = "0.4.1.post1"
description = "Kernel Library for SGLang"
readme = "README.md"
requires-python = ">=3.10"
Expand Down
2 changes: 1 addition & 1 deletion sgl-kernel/pyproject_rocm.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ build-backend = "setuptools.build_meta"

[project]
name = "sglang-kernel"
version = "0.4.1"
version = "0.4.1.post1"
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Apr 25, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

While updating the version, consider also correcting the Environment :: GPU :: NVIDIA CUDA classifier on line 20 of this file. Since this is the ROCm-specific configuration, it should likely refer to ROCm or AMD instead of NVIDIA CUDA.

description = "Kernel Library for SGLang"
readme = "README.md"
requires-python = ">=3.10"
Expand Down
2 changes: 1 addition & 1 deletion sgl-kernel/python/sgl_kernel/version.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
__version__ = "0.4.1"
__version__ = "0.4.1.post1"
6 changes: 5 additions & 1 deletion test/registered/models/test_nvidia_nemotron_3_nano.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,11 @@
from sglang.test.kits.lm_eval_kit import LMEvalMixin
from sglang.test.server_fixtures.default_fixture import DefaultServerBase

register_cuda_ci(est_time=564, suite="stage-b-test-2-gpu-large")
register_cuda_ci(
est_time=564,
suite="stage-b-test-2-gpu-large",
disabled="Temporarily disabled; failing on main.",
)

NEMOTRON_3_NANO_THINKING_ARGS = [
"--trust-remote-code",
Expand Down
Loading