Skip to main content

Unapologetically SM120-only CuTe DSL kernels for NVFP4 GEMM and MoE.

Project description

b12x is an SM120/SM121 CuTe DSL kernel library for (primarily) NVFP4 LLM inference.

It is intentionally narrow. This is not a generic CUDA kernel collection or a full model-serving stack. It does not intend to target any other GPU architectures, including SM100. It is a focused package for a small number of high-performance kernels plus the runtime glue needed to launch them cleanly from sglang/vllm.

Currently supported kernels:

  • NVFP4 fused MoE GEMM
  • NVFP4 dense GEMM
  • BF16/FP8 paged attention
  • Sparse MLA attention (for DSA/NSA only).
pip install b12x

Ask your friendly neighborhood AI agent for further information on how to use this library.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

b12x-0.15.0.tar.gz (531.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

b12x-0.15.0-py3-none-any.whl (588.3 kB view details)

Uploaded Python 3

File details

Details for the file b12x-0.15.0.tar.gz.

File metadata

  • Download URL: b12x-0.15.0.tar.gz
  • Upload date:
  • Size: 531.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.15.0.tar.gz
Algorithm Hash digest
SHA256 69f09ba5119943977386e6df7248112c25cef052c9870bad221606264d90440f
MD5 671249f964e2c92e43f82593f578c61e
BLAKE2b-256 eca085d7a34cd39915bbdc4991c221bdd0ce09bf391b78febd1d40cf6aaa038b

See more details on using hashes here.

File details

Details for the file b12x-0.15.0-py3-none-any.whl.

File metadata

  • Download URL: b12x-0.15.0-py3-none-any.whl
  • Upload date:
  • Size: 588.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.15.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2c57bc3887b39a4eda2abb41523358c26f8d7fb8c7a8bc20ca6029b2d9defcad
MD5 95c1937be32747badd81a7b922806257
BLAKE2b-256 9c44ff04835e7aaccb949d0bc30fcdd5ba2a3f5efd8977e10909069e1a7e6025

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page