{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/3"}],"enrichment":{"capability":"Humming is a JIT-compiled GEMM kernel library for quantized matrix multiplication on NVIDIA GPUs, supporting mixed quantization formats (FP16, BF16, FP8, FP4, INT8, INT4) for both dense and MoE inference workloads.","skillfed_tags":["gpu-inference","quantization","kernel-library"],"use_cases":["Deploy quantized LLMs with mixed-bit weight formats (INT4, INT6, INT8) on NVIDIA GPUs for reduced memory and latency.","Run inference with FP8 or FP4 activations and weights on newer GPUs (SM89+) for extreme compression.","Accelerate MoE model inference by using Humming's specialized MoE GEMM kernels instead of generic matrix operations.","Benchmark quantization strategies across different bit-widths and scale types without writing custom CUDA code.","Integrate quantized inference into production systems where minimal dependencies and small package size are constraints."],"what_it_does":"Humming is a lightweight, JIT-compiled GEMM kernel library optimized for quantized inference on NVIDIA GPUs. It provides high-performance matrix multiplication kernels that support a wide range of quantization formats\u2014from FP16 and BF16 down to FP4 and INT4 weights\u2014paired with various activation types (FP16, BF16, FP8, INT8, INT4). The library handles both dense matrix operations and mixture-of-experts (MoE) patterns, making it suitable for deploying quantized large language models and other inference workloads.\n\nThe package is designed to be minimal and self-contained, requiring only PyTorch and NVCC as core dependencies, with a compact footprint under 100KB. It abstracts away kernel tuning through a HummingLayer interface that automatically selects appropriate kernels for your hardware and quantization configuration. You load unquantized weights, transform them into Humming's internal format, and then run inference through the layer\u2014the library handles the low-level kernel dispatch and optimization.","worth_installing":"Yes, if you need quantized GEMM kernels for inference on NVIDIA GPUs and have the required hardware (SM75+) and Python environment (\u22653.10). The package is actively maintained, has no known vulnerabilities, and offers broad quantization format support. However, verify the license terms before use, and confirm that your CUDA and PyTorch versions are compatible\u2014the fact sheet does not specify exact version constraints beyond the architecture requirement."},"id":"humming-kernels","links":{"html":"https://skillfed.io/packages/humming-kernels","md":"https://skillfed.io/packages/humming-kernels.md","pypi":"https://pypi.org/project/humming-kernels/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-07-31","license_spdx":null,"license_treatment":"unclear","name":"humming-kernels","python_support":"supports_current","summary":"Quantization GEMM Kernel"},"popularity":{"monthly_downloads":1421523,"position":3923,"tier":"top_5000"},"security":{"n_vulnerabilities":0},"version":"0.1.12"}