Skip to content

maxsim

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History

maxsim

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 
bench.py
bench.py
 
 
bench.rs
bench.rs
 
 

README.md

MaxSim Benchmarks

ColBERT-style late-interaction scoring benchmarks comparing NumKong against ndarray.

Rust

Library Precision GSO/s
numkong::MaxSimPackedMatrix::score f32 → f64 1483.41
numkong::MaxSimPackedMatrix::score bf16 → f32 983.57
numkong::MaxSimPackedMatrix::score f16 → f32 980.33
ndarray Q @ Dᵀ max-reduce f32 → f32 58.37

Python

Library Precision GSO/s
numkong.maxsim_packed f32 → f64 2425.72
numpy matmul f32 → f32 1525.56
numkong.maxsim_packed bf16 → f32 1236.30
numkong.maxsim_packed f16 → f32 696.78

Run It

Rust

# Default 2048×2048×2048 workload
cargo bench --bench bench_maxsim --features bench_maxsim

# Smaller 128×128×256 workload
NUMWARS_DIMS_HEIGHT=128 NUMWARS_DIMS_WIDTH=128 NUMWARS_DIMS_DEPTH=256 \
cargo bench --bench bench_maxsim --features bench_maxsim

# Focus on one dtype
NUMWARS_FILTER="maxsim/f32" \
cargo bench --bench bench_maxsim --features bench_maxsim

Python

uv run --with numkong,numpy,tabulate,ml_dtypes python maxsim/bench.py