Kernels: MiniMaxAI / msa like 24 Follow MiniMax 6.89k

This is the repository card of kernels-community/msa that has been pushed on the Hub. It was built to be used with the kernels library. This card was automatically generated.

How to use

# make sure `kernels` is installed: `pip install -U kernels`
from kernels import get_kernel
kernel_module = get_kernel("kernels-community/msa", version=0)
sparse_atten_func = kernel_module.sparse_atten_func
sparse_atten_func(...)

Available functions

• `sparse_atten_func`
• `sparse_atten_nvfp4_kv_func`
• `sparse_decode_atten_func`
• `SparseDecodePagedAttentionWrapper`
• `fp4_indexer_block_scores`
• `build_k2q_csr`
• `SparseK2qCsrBuilderSm100`
• `Nvfp4QuantizedTensor`
• `quantize_bf16_to_nvfp4_128x4`
• `quantize_kv_bf16_to_nvfp4_128x4`
• `dequantize_nvfp4_128x4_to_bf16`
• `swizzle_nvfp4_scale_to_128x4`
• `nvfp4_global_scale_from_amax`

Benchmarks

No benchmark available yet.

Source code

Source code of this kernel originally comes from <https://github.com/MiniMax-AI/MSA> and it was repurposed for compatibility with `kernels`.

Use this kernel

Downloads last month 2

other

Supported hardwares new

CUDA

10.0

B200

192GB

OS linuxArch x86\_64aarch64