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-0.12.3.tar.gz (456.0 kB view details)

Uploaded Source

Built Distribution

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

b12x-0.12.3-py3-none-any.whl (514.6 kB view details)

Uploaded Python 3

File details

Details for the file b12x-0.12.3.tar.gz.

File metadata

  • Download URL: b12x-0.12.3.tar.gz
  • Upload date:
  • Size: 456.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.12.3.tar.gz
Algorithm Hash digest
SHA256 ec9017b1d70ec7c0cd4972caeca1bbcf79ff13caa9808b43a8370fae8d256ba6
MD5 c2807985474e24f55bfbc20f608a66af
BLAKE2b-256 5ea3f9499b5f04c4faddafdabb210b2f4d06d85eb7d0280e223b8c57de799862

See more details on using hashes here.

File details

Details for the file b12x-0.12.3-py3-none-any.whl.

File metadata

  • Download URL: b12x-0.12.3-py3-none-any.whl
  • Upload date:
  • Size: 514.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.12.3-py3-none-any.whl
Algorithm Hash digest
SHA256 d8fd2c5a37e80fb5c362c294dab6be20278a93486dd8501a51cf1207fff2be27
MD5 5cb1e248b50c3b3b05e8d0581fca25c1
BLAKE2b-256 42709e6be88607b9bd8d1ad7a0df63b3f67dd45e276680ea9ec596ea3b25020d

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