Bump Liger packages to 0.8.3 (#1471)

## Summary

- bump the shared public version from `0.8.2` to `0.8.3`
- update both `liger-kernel` and `liger-cute-kernels`, since the native
package resolves its version from the root `pyproject.toml`
- add `liger-kernel[lck]` as an optional install path
- pin the extra to `liger-cute-kernels==0.8.3` so the Python and native
distributions cannot drift across releases
- document stable and editable `lck` extra installation

## Resulting installs

```bash
pip install liger-kernel
pip install "liger-kernel[lck]"
```

The second command installs the normal Liger dependencies plus the
exactly matching standalone native wheel.

## Validation

- root wheel: `liger_kernel-0.8.3-py3-none-any.whl`
- root wheel metadata includes `Provides-Extra: lck`
- root wheel metadata includes `liger-cute-kernels==0.8.3; extra ==
"lck"`
- standalone LCK package metadata resolves to `0.8.3`
- targeted LCK version tests pass
- Ruff check and format checks pass for `setup.py`

---------

Co-authored-by: jkolehma <[email protected]>
Co-authored-by: Copilot <[email protected]>

README.md

@@ -152,6 +152,7 @@ pip install -e ".[dev]" --extra-index-url https://triton-ascend.osinfra.cn/pypi/
 - `cuda-tile`: Required when enabling the optional cuTile backend on CUDA. Use this when your environment already provides CUDA Toolkit 13.1 or newer, or an existing tileiras compiler installation.
 - `cuda-tile[tileiras]`: Required when enabling the optional cuTile backend with the tileiras compiler installed directly into your Python environment.
 - `nvidia-cutlass-dsl >= 4.6.0`: Required when enabling the optional CuTe DSL backend on CUDA (the CUDA-only Python DSL shipped with NVIDIA CUTLASS, `import cutlass.cute`). Targets Hopper (SM90) and Blackwell (SM100/SM110).
+- `liger-cute-kernels`: Native CUTLASS + NVSHMEM kernels for Hopper and Blackwell, installed at the exact matching Liger version by the `lck` extra.
 
 > **Note:**
 > Our kernels inherit the full spectrum of hardware compatibility offered by [Triton](https://github.com/triton-lang/triton).
@@ -162,6 +163,12 @@ To install the stable version:
 $ pip install liger-kernel
 ```
 
+To also install the matching native Liger communication kernels:
+
+```bash
+$ pip install "liger-kernel[lck]"
+```
+
 To install the nightly version:
 
 ```bash
@@ -197,6 +204,9 @@ pip install -e ".[cutile-tileiras]"
 # Setup CuTe DSL (NVIDIA CUTLASS Python DSL) Dependencies
 pip install -e ".[cutedsl]"
 
+# Setup native Liger communication kernels
+pip install -e ".[lck]"
+
 ```
 
 ### Enable cuTile Backend

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "liger_kernel"
-version = "0.8.2"
+version = "0.8.3"
 description = "Efficient Triton kernels for LLM Training"
 urls = { "Homepage" = "https://github.com/linkedin/Liger-Kernel" }
 readme = { file = "README.md", content-type = "text/markdown" }

setup.py

@@ -1,13 +1,24 @@
 # setup.py
 
+import re
 import subprocess
 
+from pathlib import Path
 from typing import Literal
 
 from setuptools import find_packages
 from setuptools import setup
 
 
+def get_project_version() -> str:
+    """Read the public package version shared with liger-cute-kernels."""
+    pyproject = Path(__file__).resolve().parent / "pyproject.toml"
+    match = re.search(r'(?m)^version\s*=\s*"([^"]+)"\s*$', pyproject.read_text())
+    if match is None:
+        raise RuntimeError(f"could not read the project version from {pyproject}")
+    return match.group(1)
+
+
 def get_default_dependencies():
     """Determine the appropriate dependencies based on detected hardware."""
     platform = get_platform()
@@ -49,6 +60,9 @@ def get_optional_dependencies():
         # per-call cost dominates: RMSNorm forward measured 53us -> 15us on B200.
         "apache-tvm-ffi>=0.1.0",
     ]
+    lck_deps = [
+        f"liger-cute-kernels=={get_project_version()}",
+    ]
     dev_deps = [
         "transformers>=4.52.0",
         "matplotlib>=3.7.2",
@@ -68,6 +82,7 @@ def get_optional_dependencies():
         "cutile": cutile_deps,
         "cutile-tileiras": cutile_tileiras_deps,
         "cutedsl": cutedsl_deps,
+        "lck": lck_deps,
         "dev": dev_deps,
     }