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-0.9.5.tar.gz (363.8 kB view details)

Uploaded Source

Built Distribution

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

b12x-0.9.5-py3-none-any.whl (415.8 kB view details)

Uploaded Python 3

File details

Details for the file b12x-0.9.5.tar.gz.

File metadata

  • Download URL: b12x-0.9.5.tar.gz
  • Upload date:
  • Size: 363.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.9.5.tar.gz
Algorithm Hash digest
SHA256 73dbe09596a94e44388203845770b50b3138398fe6699e8eb8db2dac5addcf0c
MD5 4177afef3b97c307aaaa3920e16a6b8f
BLAKE2b-256 c9dabce4308e2bb4c450a04b4e1f25f2dca996f8aabbf84a353bc6774c1649f4

See more details on using hashes here.

File details

Details for the file b12x-0.9.5-py3-none-any.whl.

File metadata

  • Download URL: b12x-0.9.5-py3-none-any.whl
  • Upload date:
  • Size: 415.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.9.5-py3-none-any.whl
Algorithm Hash digest
SHA256 d9a04df81fb80f1052660e538dd6914f0cb8208cbd19af8cfebf190aff82f593
MD5 e1e314902b67124d1b14a935e7eeda6d
BLAKE2b-256 f8b48171b90cc64a2ad3b665199cf701a9cf7372b4b379b49f00eb8e1c1f1f31

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