Quick Start

flashinfer-bench run --local /path/to/flashinfer-trace

# Print a summary: pass/fail counts and author rankings by average speedup
flashinfer-bench report summary --local /path/to/flashinfer-trace

# Show the best solution for every definition
flashinfer-bench report best --local /path/to/flashinfer-trace

# Run with custom configuration
flashinfer-bench run --local /path/to/flashinfer-trace \
  --warmup-runs 10 \
  --iterations 100 \
  --num-trials 5 \
  --rtol 1e-3 \
  --atol 1e-3

# Run specific definitions or solutions
flashinfer-bench run --local /path/to/flashinfer-trace \
  --definitions gemm_n5120_k2048 rmsnorm_h128 \
  --solutions solution_name_1 solution_name_2...

# Resume interrupted runs
flashinfer-bench run --local /path/to/flashinfer-trace --resume

from flashinfer_bench.bench import Benchmark, BenchmarkConfig
from flashinfer_bench.data import TraceSet

# Load trace dataset
trace_set = TraceSet.from_path("/path/to/flashinfer-trace")

# Configure benchmark (uses bundled eval_config.yaml defaults)
config = BenchmarkConfig.default(
    warmup_runs=10,
    iterations=100,
    num_trials=5,
    rtol=1e-3,
    atol=1e-3,
)

# Or load from a custom YAML config
config = BenchmarkConfig.from_yaml("my_config.yaml", iterations=200)

# Run benchmark
benchmark = Benchmark(trace_set, config)
benchmark.run_all(save_results=True)

# Get best solution for a definition, e.g. gemm_n5120_k2048
best_trace = trace_set.get_best_trace("gemm_n5120_k2048")
if best_trace:
    print(f"Best solution: {best_trace.solution}")
    print(f"Speedup: {best_trace.evaluation.performance.speedup_factor:.2f}×")

import flashinfer_bench  # Import to install adapters
from flashinfer.norm import fused_add_rmsnorm

# Your FlashInfer code runs as normal
# But optimized kernels are automatically applied when available