Humming
Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for quantized inference.
Key Features
- High Flexibility
- Supports inference for any weight type under 8-bit across FP16 / BF16 / FP8 / FP4 / INT8 / INT4 activations (provided the activation's dynamic range covers the weight type).
- Supports various quantization strategies.
- Supports various scale types (BF16, FP16, E4M3, E5M2, and UE8M0).
- Supports both Dense GEMM and MoE GEMM.
- High Compatibility: supports all NVIDIA GPUs from SM75+ (Turing architecture) and beyond.
- High Performance
- Delivers State-of-the-Art (SOTA) throughput and efficiency across a wide range of computational scenarios.
- Ultra-Lightweight
- Minimal dependencies: Requires only PyTorch and NVCC.
- Compact footprint: The package size is only 100+KB.
Support Matrix
| Activation Type | Supported Devices | Supported Weight Types |
|---|---|---|
| FP16 (e5m10) | SM75+ | • Symmetric INT1-8 • INT1-8 with dynamic zero point • Arbitrary signed FP (kBits ≤ 8, kExp ≤ 5) |
| BF16 (e8m7) | SM80+ | • Symmetric INT1-8 • INT1-8 with dynamic zero point • Arbitrary signed FP (kBits ≤ 8) |
| FP8 (e4m3) | SM89+ | • Symmetric INT1-5 • INT1-4 with dynamic zero point • Arbitrary signed FP (kExp ≤ 4, kMan ≤ 3) |
| FP8 (e5m2) | SM89+ | • Symmetric INT1-4 • INT1-3 with dynamic zero point • Arbitrary signed FP (kExp ≤ 5, kMan ≤ 2) |
| FP4 (e2m1) | SM120+ | • Symmetric INT1-3 • INT1-2 with dynamic zero point • Arbitrary signed FP (kExp ≤ 2, kMan ≤ 1) |
| INT8 | SM75+ | • Symmetric INT1-8 • INT1-7 with dynamic zero point |
| INT4 | SM80+ | • Symmetric INT1-4 • INT1-3 with dynamic zero point |
Getting Started
Installation
pip install humming-kernels
To also install CUDA dependencies, choose the extra matching your PyTorch CUDA version:
pip install "humming-kernels[cu12]" # CUDA 12
pip install "humming-kernels[cu13]" # CUDA 13
Or install from source:
pip install git+https://github.com/vllm-project/humming.git
Usage Example
import torch
from humming.layer import HummingLayer
layer = HummingLayer(
shape_n=8192,
shape_k=8192,
weight_config={"dtype": "int6"},
torch_dtype=torch.float16,
).cuda()
weight = torch.randn((8192, 8192), dtype=torch.float16, device="cuda:0")
inputs = torch.randn((128, 8192), dtype=torch.float16, device="cuda:0")
# Load unquantized weight and quantize to layer quantization format
layer.load_from_unquantized(weight)
# Transform weight to humming format and prepare default kernels
layer.transform()
# Run quantized GEMM (tuning_config is optional, auto-selected by default)
output = layer(inputs)
print("Quantized GEMM Output:")
print(output)
print("\nReference Output:")
print(inputs.matmul(weight.T))
Acknowledgement
This project is highly inspired by
- DeepGEMM
- Marlin Kernel and vLLM Marlin Kernel
- lmdeploy GEMM kernel
- CUTLASS
1 maintainer
Metadata
1 maintainer
Release files for humming-kernels 0.1.19
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| humming_kernels-0.1.19.tar.gz | 428.2 kB | With provenance | Details for humming_kernels-0.1.19.tar.gz |
Built distributions (wheels)
| File | Actions Reset | |||
|---|---|---|---|---|
| humming_kernels-0.1.19-cp311-abi3-win_arm64.whl | CPython 3.11 | abi3 | Windows ARM64 | Details for humming_kernels-0.1.19-cp311-abi3-win_arm64.whl |
| humming_kernels-0.1.19-cp311-abi3-win_amd64.whl | CPython 3.11 | abi3 | Windows x86-64 | Details for humming_kernels-0.1.19-cp311-abi3-win_amd64.whl |
| humming_kernels-0.1.19-cp310-abi3-manylinux_2_28_x86_64.whl | CPython 3.10 | abi3 | Linux glibc 2.28+ x86-64 | Details for humming_kernels-0.1.19-cp310-abi3-manylinux_2_28_x86_64.whl |
| humming_kernels-0.1.19-cp310-abi3-manylinux_2_28_aarch64.whl | CPython 3.10 | abi3 | Linux glibc 2.28+ ARM64 | Details for humming_kernels-0.1.19-cp310-abi3-manylinux_2_28_aarch64.whl |
Total release size: 2.6 MB
Release files / humming_kernels-0.1.19.tar.gz
| Download URL | humming_kernels-0.1.19.tar.gz |
|---|---|
| Size | 428.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3c6c7ef0e55ef6b97b8b0d4134f7f34cf988df22f7885bff27aa0b30fbbd8e65
|
|
BLAKE2b-256 checksum How to use checksums |
6ec44ca7fd5042fed448b62874f1d2886c93c0ac78da11cd5548f926e0483f64
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.
Transparency logRelease files / humming_kernels-0.1.19-cp311-abi3-win_arm64.whl
| Download URL | humming_kernels-0.1.19-cp311-abi3-win_arm64.whl |
|---|---|
| Size | 546.3 kB |
| Tags | CPython 3.11 Windows ARM64 abi3 |
|
SHA-256 checksum How to use checksums |
5f553c8fe8ff680ebee25edade11b16f6f927d5adb95e203277dd08cea7a8fcc
|
|
BLAKE2b-256 checksum How to use checksums |
1949716ff694dacee6eb04a55f6f1e61599d5b9e3873caeab7004fb8144ea41b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.
Transparency logRelease files / humming_kernels-0.1.19-cp311-abi3-win_amd64.whl
| Download URL | humming_kernels-0.1.19-cp311-abi3-win_amd64.whl |
|---|---|
| Size | 557.1 kB |
| Tags | CPython 3.11 Windows x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
52a326aa33919eeaa040b4b9f28f8b5ce1ee061f5f52169a3a1be42c44a3a8e3
|
|
BLAKE2b-256 checksum How to use checksums |
5deaf8b9343f3e04ba92f3be93d9e9cee5ff1d9a3babdf7dc385908be5a5e215
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.
Transparency logRelease files / humming_kernels-0.1.19-cp310-abi3-manylinux_2_28_x86_64.whl
| Download URL | humming_kernels-0.1.19-cp310-abi3-manylinux_2_28_x86_64.whl |
|---|---|
| Size | 556.0 kB |
| Tags | CPython 3.10 Linux glibc 2.28+ x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
16ad0c8e9c2d5a8db739bdb97bcc510cedc9dc4c4c111098cbb2d7ac9c1dd973
|
|
BLAKE2b-256 checksum How to use checksums |
afa1d6c92ed0290b8e1322d7b9ffb3fafe4f2af51ba9b564fa561c036a402266
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.
Transparency logRelease files / humming_kernels-0.1.19-cp310-abi3-manylinux_2_28_aarch64.whl
| Download URL | humming_kernels-0.1.19-cp310-abi3-manylinux_2_28_aarch64.whl |
|---|---|
| Size | 547.1 kB |
| Tags | CPython 3.10 Linux glibc 2.28+ ARM64 abi3 |
|
SHA-256 checksum How to use checksums |
13038de14ed2910bcb46f0147d9935c6cac835045e07b3f38c2137d76b77bc4c
|
|
BLAKE2b-256 checksum How to use checksums |
693429856875ef58ca87eaa31acf3d37466e8523025c709ef52478492060dc73
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.
Transparency logSecurity for humming-kernels 0.1.19
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 5 files in this release have been uploaded with provenance metadata.
Attestation for humming_kernels-0.1.19.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
