From 2dfe464e5adb6c7b528c872369c0617b4464c308 Mon Sep 17 00:00:00 2001
From: Dnoob <dxpouo@gmail.com>
Date: Thu, 3 Sep 2026 17:57:55 +0800
Subject: [PATCH] style: apply black line-length 100 and pin it in
 pyproject.toml

Signed-off-by: Dnoob <dxpouo@gmail.com>
---
 pyproject.toml                                | 109 ++++++++++--------
 rl_engine/integrations/vllm_runtime.py        |   6 +-
 .../kernels/ops/cuda/attention/flash_attn.py  |  10 +-
 3 files changed, 61 insertions(+), 64 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index ca3b0c5d..216eec05 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,55 +1,62 @@
-[build-system]
-requires = ["setuptools>=64", "wheel"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "RL-Kernel"
-version = "0.1.0"
-description = "High-performance RL training engine focused on kernel fusion and memory efficiency."
-readme = "README.md"
-requires-python = ">=3.10"
-license = {text = "Apache-2.0"}
-authors = [
-    {name = "RL-Kernel Contributors"}
-]
-dependencies = [
-    "torch>=2.4.1",
-    "tabulate",
-    "numpy",
-    "accelerate",
-    "transformers==5.13.1",
-]
-
-[project.entry-points."vllm.general_plugins"]
-rl_kernel = "rl_engine.integrations.vllm_runtime:register_vllm_plugin"
-
-[project.optional-dependencies]
-cuda = ["flashinfer-python>=0.1.6", "nvidia-ml-py"]
+[build-system]
+requires = ["setuptools>=64", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "RL-Kernel"
+version = "0.1.0"
+description = "High-performance RL training engine focused on kernel fusion and memory efficiency."
+readme = "README.md"
+requires-python = ">=3.10"
+license = {text = "Apache-2.0"}
+authors = [
+    {name = "RL-Kernel Contributors"}
+]
+dependencies = [
+    "torch>=2.4.1",
+    "tabulate",
+    "numpy",
+    "accelerate",
+    "transformers==5.13.1",
+]
+
+[project.entry-points."vllm.general_plugins"]
+rl_kernel = "rl_engine.integrations.vllm_runtime:register_vllm_plugin"
+
+[project.optional-dependencies]
+cuda = ["flashinfer-python>=0.1.6", "nvidia-ml-py"]
 rocm = ["aiter"]
 vllm = ["vllm>=0.6.0"]
 drift-viewer = ["Pillow>=10", "PySide6>=6.6"]
 dev = ["pytest", "black", "isort", "ruff", "mypy", "pre-commit"]
-
-[tool.setuptools.packages.find]
-where = ["."]
-include = ["rl_engine*"]
-
-[tool.ruff]
-line-length = 100
-
-[tool.ruff.lint]
-select = ["E", "F", "B"]
-ignore = []
-
-[tool.ruff.lint.per-file-ignores]
-"__init__.py" = ["F401"]
-
-[tool.mypy]
-ignore_missing_imports = true
-follow_imports = "silent"
-
-[tool.pytest.ini_options]
-markers = [
-    "smoke_operator: temporary smoke-only operator plumbing tests",
-    "unit: CPU-safe unit tests",
-]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["rl_engine*"]
+
+[tool.black]
+line-length = 100
+
+[tool.isort]
+profile = "black"
+line_length = 100
+
+[tool.ruff]
+line-length = 100
+
+[tool.ruff.lint]
+select = ["E", "F", "B"]
+ignore = []
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401"]
+
+[tool.mypy]
+ignore_missing_imports = true
+follow_imports = "silent"
+
+[tool.pytest.ini_options]
+markers = [
+    "smoke_operator: temporary smoke-only operator plumbing tests",
+    "unit: CPU-safe unit tests",
+]
diff --git a/rl_engine/integrations/vllm_runtime.py b/rl_engine/integrations/vllm_runtime.py
index ade13cab..6351f0ab 100644
--- a/rl_engine/integrations/vllm_runtime.py
+++ b/rl_engine/integrations/vllm_runtime.py
@@ -475,11 +475,7 @@ def strict_row_parallel_forward(instance: Any, input_: torch.Tensor) -> Any:
                 )[instance.tp_rank].contiguous()
 
             assert instance.quant_method is not None
-            bias_ = (
-                None
-                if (instance.tp_rank > 0 or instance.skip_bias_add)
-                else instance.bias
-            )
+            bias_ = None if (instance.tp_rank > 0 or instance.skip_bias_add) else instance.bias
             output_parallel = instance.quant_method.apply(instance, input_parallel, bias_)
 
             if instance.reduce_results and instance.tp_size > 1:
diff --git a/rl_engine/kernels/ops/cuda/attention/flash_attn.py b/rl_engine/kernels/ops/cuda/attention/flash_attn.py
index 9ad510b3..e57cdeb5 100644
--- a/rl_engine/kernels/ops/cuda/attention/flash_attn.py
+++ b/rl_engine/kernels/ops/cuda/attention/flash_attn.py
@@ -130,9 +130,7 @@ def precompile_training(
         tensors, RNG state, or distributed collectives.
         """
         if torch.version.hip is not None:
-            raise StrictFlashAttentionUnavailable(
-                "FA4 CUDA precompile is unavailable on ROCm"
-            )
+            raise StrictFlashAttentionUnavailable("FA4 CUDA precompile is unavailable on ROCm")
         if not torch.cuda.is_available():
             raise StrictFlashAttentionUnavailable(
                 "FA4 CUDA precompile requires an available CUDA device"
@@ -144,11 +142,7 @@ def precompile_training(
         if head_dim <= 0 or sequence_length <= 0:
             raise ValueError("head_dim and sequence_length must be positive")
 
-        target = (
-            torch.device("cuda", torch.cuda.current_device())
-            if device is None
-            else device
-        )
+        target = torch.device("cuda", torch.cuda.current_device()) if device is None else device
         if target.type != "cuda":
             raise ValueError("strict FA4 training precompile requires a CUDA device")