+
+▶ code
+▼ output
+ ▶ uv-logs
+ |
+Cell: combine | 4.29s
+ |
+
+Raw
+
+
+
+
+
+
+1
+2
+3
+4
+5
+6
+7
+8
+9
+10
+11
+12
+13
+14
+15
+16
+17
+18
+19
+20
+21
+22
+23
+24
+25
+26
+27
+
+
+
+
+
+
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+# "numpy",
+# "torch==2.8.0",
+# "kernels-benchmark-tools",
+# "matplotlib",
+# ]
+#
+# [tool.uv.sources]
+# kernels-benchmark-tools = { path = "../../../../../tools", editable = true }
+# ///
+from kernels_benchmark_tools.core.visuals import generate_combined_results
+
+# Map display names to uvnote environment variables
+cache_env_map = {
+ "HF Kernels SwiGLU": "UVNOTE_FILE_HF_KERNELS_SWIGLU_BENCHMARK",
+ "PyTorch SwiGLU": "UVNOTE_FILE_TORCH_SWIGLU_BENCHMARK",
+ # "Compiled SwiGLU": "UVNOTE_FILE_COMPILED_SWIGLU_BENCHMARK",
+}
+
+# Generate combined results with visualization
+generate_combined_results(
+ cache_env_map=cache_env_map,
+ output_filename="activation.jsonl",
+ svg_filename="latency.svg"
+)
+
+
+
+====================================================================== +LOADING BENCHMARK DATA +====================================================================== +✓ HF Kernels SwiGLU : /__w/kernels-benchmarks/kernels-benchmarks/benches/activation/impls/.uvnote/cache/2775e6386f1caf1fda935a997130c06dcaf7641efb0db21560c35301fdabfd9b +✓ PyTorch SwiGLU : /__w/kernels-benchmarks/kernels-benchmarks/benches/activation/impls/.uvnote/cache/661ca38adec8893d7c284140e922da661f0afcea4aaff6a3bf48a6494ce7c6eb + + ✓ Found HF Kernels SwiGLU + Path: /__w/kernels-benchmarks/kernels-benchmarks/benches/activation/impls/.uvnote/cache/2775e6386f1caf1fda935a997130c06dcaf7641efb0db21560c35301fdabfd9b/activation.jsonl + ✓ Found PyTorch SwiGLU + Path: /__w/kernels-benchmarks/kernels-benchmarks/benches/activation/impls/.uvnote/cache/661ca38adec8893d7c284140e922da661f0afcea4aaff6a3bf48a6494ce7c6eb/activation.jsonl + +====================================================================== +Summary: 2 found, 0 skipped, 0 missing +====================================================================== + +COMBINED BENCHMARK SUMMARY + +impl wl p50(ms) ok +hf_kernels_swiglu cuda_T128_D1024 0.03 True +hf_kernels_swiglu cuda_T128_D2048 0.03 True +hf_kernels_swiglu cuda_T128_D768 0.02 True +hf_kernels_swiglu cuda_T256_D1024 0.03 True +hf_kernels_swiglu cuda_T256_D2048 0.03 True +hf_kernels_swiglu cuda_T256_D768 0.03 True +hf_kernels_swiglu cuda_T512_D1024 0.03 True +hf_kernels_swiglu cuda_T512_D2048 0.03 True +hf_kernels_swiglu cuda_T512_D768 0.03 True +torch_eager cuda_T128_D1024 0.05 True +torch_eager cuda_T128_D2048 0.05 True +torch_eager cuda_T128_D768 0.04 True +torch_eager cuda_T256_D1024 0.05 True +torch_eager cuda_T256_D2048 0.05 True +torch_eager cuda_T256_D768 0.05 True +torch_eager cuda_T512_D1024 0.05 True +torch_eager cuda_T512_D2048 0.05 True +torch_eager cuda_T512_D768 0.05 True + +GENERATING COMBINED VISUALIZATION + +Loaded 18 records +✓ Visualization saved as latency.svg +Saved latency.png +✓ Visualization saved as latency.svg +✓ SVG visualization ready! + +ANALYSIS COMPLETE +Total implementations analyzed: 2 + +Implementations included: + ✓ HF Kernels SwiGLU + ✓ PyTorch SwiGLU +
+
+
+▶ UV Install Logs
+
+