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-0.14.1.tar.gz (493.4 kB view details)

Uploaded Source

Built Distribution

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

b12x-0.14.1-py3-none-any.whl (548.3 kB view details)

Uploaded Python 3

File details

Details for the file b12x-0.14.1.tar.gz.

File metadata

  • Download URL: b12x-0.14.1.tar.gz
  • Upload date:
  • Size: 493.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.14.1.tar.gz
Algorithm Hash digest
SHA256 f51838b4ecbb07c3c96a2cf711caad609440ddc347b6b2b15272a2b1cc63988f
MD5 4183dfbfcf1b2e2bf27cf5ffe4024f7d
BLAKE2b-256 18cedcffbae9311da94374dfc0853d1ad03db58b6c6c81c0d8abaddb5e07f00f

See more details on using hashes here.

File details

Details for the file b12x-0.14.1-py3-none-any.whl.

File metadata

  • Download URL: b12x-0.14.1-py3-none-any.whl
  • Upload date:
  • Size: 548.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for b12x-0.14.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d69ada6426463006b7514f4c195ff8e9c6a3666dc93385c5e7c8f55bfd4212c8
MD5 bc73c8cc62c8e79f5b188a1b0336ac0e
BLAKE2b-256 55ed4d5b175fc3ad14d28c81471be8b788f0028cae36543086131841c271ab23

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