fix ruff errors and formatting

test/micro_tpt.py

@@ -58,7 +58,8 @@ class GraphWrapper:
             self.graph = torch.cuda.CUDAGraph()
             with torch.cuda.graph(self.graph):
                 self.static_output = self.model(
-                    input_ids=self.static_input, attention_mask=self.static_attention_mask
+                    input_ids=self.static_input,
+                    attention_mask=self.static_attention_mask,
                 )
             self.use_cuda_graph = True
         else:
@@ -82,7 +83,10 @@ class GraphWrapper:
     def _warmup(self, num_warmup: int = 3):
         with torch.no_grad():
             for _ in range(num_warmup):
-                self.model(input_ids=self.static_input, attention_mask=self.static_attention_mask)
+                self.model(
+                    input_ids=self.static_input,
+                    attention_mask=self.static_attention_mask,
+                )
 
     def __call__(self, input_ids: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
         if self.use_cuda_graph:
@@ -261,7 +265,10 @@ class Benchmark:
                                 # print size
                                 print(f"in_features: {in_features}, out_features: {out_features}")
                                 new_module = bnb.nn.Linear8bitLt(
-                                    in_features, out_features, bias=bias, has_fp16_weights=False
+                                    in_features,
+                                    out_features,
+                                    bias=bias,
+                                    has_fp16_weights=False,
                                 )
 
                                 # Copy weights and bias
@@ -350,8 +357,6 @@ class Benchmark:
                 # Try xformers if available (only on CUDA)
                 if torch.cuda.is_available():
                     try:
-                        from xformers.ops import memory_efficient_attention  # noqa: F401
-
                         if hasattr(model, "enable_xformers_memory_efficient_attention"):
                             model.enable_xformers_memory_efficient_attention()
                             print("- Enabled xformers memory efficient attention")
@@ -427,7 +432,11 @@ class Benchmark:
             else "cpu"
         )
         return torch.randint(
-            0, 1000, (batch_size, self.config.seq_length), device=device, dtype=torch.long
+            0,
+            1000,
+            (batch_size, self.config.seq_length),
+            device=device,
+            dtype=torch.long,
         )
 
     def _run_inference(

test/sanity_checks/README.md

@@ -7,7 +7,7 @@ This directory contains comprehensive sanity checks for the Leann system, ensuri
 ### `test_distance_functions.py`
 Tests all supported distance functions across DiskANN backend:
 - ✅ **MIPS** (Maximum Inner Product Search)
-- ✅ **L2** (Euclidean Distance) 
+- ✅ **L2** (Euclidean Distance)
 - ✅ **Cosine** (Cosine Similarity)
 
 ```bash
@@ -27,7 +27,7 @@ uv run python tests/sanity_checks/test_l2_verification.py
 ### `test_sanity_check.py`
 Comprehensive end-to-end verification including:
 - Distance function testing
-- Embedding model compatibility  
+- Embedding model compatibility
 - Search result correctness validation
 - Backend integration testing
 
@@ -64,7 +64,7 @@ When all tests pass, you should see:
 ```
 📊 测试结果总结:
   mips      : ✅ 通过
-  l2        : ✅ 通过  
+  l2        : ✅ 通过
   cosine    : ✅ 通过
 
 🎉 测试完成!
@@ -98,7 +98,7 @@ pkill -f "embedding_server"
 
 ### Typical Timing (3 documents, consumer hardware):
 - **Index Building**: 2-5 seconds per distance function
-- **Search Query**: 50-200ms 
+- **Search Query**: 50-200ms
 - **Recompute Mode**: 5-15 seconds (higher accuracy)
 
 ### Memory Usage:
@@ -117,4 +117,4 @@ These tests are designed to be run in automated environments:
     uv run python tests/sanity_checks/test_l2_verification.py
 ```
 
-The tests are deterministic and should produce consistent results across different platforms.
+The tests are deterministic and should produce consistent results across different platforms.

test/sanity_checks/benchmark_embeddings.py

@@ -115,7 +115,13 @@ def main():
     # --- Plotting ---
     print("\n--- Generating Plot ---")
     plt.figure(figsize=(10, 6))
-    plt.plot(BATCH_SIZES, results_torch, marker="o", linestyle="-", label=f"PyTorch ({device})")
+    plt.plot(
+        BATCH_SIZES,
+        results_torch,
+        marker="o",
+        linestyle="-",
+        label=f"PyTorch ({device})",
+    )
     plt.plot(BATCH_SIZES, results_mlx, marker="s", linestyle="-", label="MLX")
 
     plt.title(f"Embedding Performance: MLX vs PyTorch\nModel: {MODEL_NAME_TORCH}")

test/simple_mac_tpt_test.py

@@ -170,7 +170,11 @@ class Benchmark:
 
     def _create_random_batch(self, batch_size: int) -> torch.Tensor:
         return torch.randint(
-            0, 1000, (batch_size, self.config.seq_length), device=self.device, dtype=torch.long
+            0,
+            1000,
+            (batch_size, self.config.seq_length),
+            device=self.device,
+            dtype=torch.long,
         )
 
     def _run_inference(self, input_ids: torch.Tensor) -> float:
@@ -256,7 +260,11 @@ def run_mlx_benchmark():
     """Run MLX-specific benchmark"""
     if not MLX_AVAILABLE:
         print("MLX not available, skipping MLX benchmark")
-        return {"max_throughput": 0.0, "avg_throughput": 0.0, "error": "MLX not available"}
+        return {
+            "max_throughput": 0.0,
+            "avg_throughput": 0.0,
+            "error": "MLX not available",
+        }
 
     config = BenchmarkConfig(model_path="mlx-community/all-MiniLM-L6-v2-4bit", use_mlx=True)
 
@@ -265,7 +273,11 @@ def run_mlx_benchmark():
         results = benchmark.run()
 
         if not results:
-            return {"max_throughput": 0.0, "avg_throughput": 0.0, "error": "No valid results"}
+            return {
+                "max_throughput": 0.0,
+                "avg_throughput": 0.0,
+                "error": "No valid results",
+            }
 
         max_throughput = max(results[batch_size]["throughput"] for batch_size in results)
         avg_throughput = np.mean([results[batch_size]["throughput"] for batch_size in results])