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-0.12.1.tar.gz (455.6 kB view details)

Uploaded Source

Built Distribution

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

b12x-0.12.1-py3-none-any.whl (514.2 kB view details)

Uploaded Python 3

File details

Details for the file b12x-0.12.1.tar.gz.

File metadata

  • Download URL: b12x-0.12.1.tar.gz
  • Upload date:
  • Size: 455.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.12.1.tar.gz
Algorithm Hash digest
SHA256 eef1f618b367218e4a4b2719e0faa8606ecaa6cc949a437df0879e033dafe26a
MD5 baa0db5c1f524f805684b242ec7bae0e
BLAKE2b-256 4b2681860804ce328fbf1716e96aa47650976d890589e78a246eaf30042f1c46

See more details on using hashes here.

File details

Details for the file b12x-0.12.1-py3-none-any.whl.

File metadata

  • Download URL: b12x-0.12.1-py3-none-any.whl
  • Upload date:
  • Size: 514.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.12.1-py3-none-any.whl
Algorithm Hash digest
SHA256 6ae513b139dc33e7faf6a5a3db871f8b91869f01a20ac3ce6d3624f407c06a69
MD5 dca08e59e806b25201d52ed130b8b73b
BLAKE2b-256 1df87f66256c2916fe186ec89870b0eeb796f56f69bea654ab7bff6676f35861

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