flashinfer.fp4_quantization

Note

Starting in FlashInfer 0.6.12, the canonical home for FP4 quantization APIs is flashinfer.quantization.

flashinfer.fp4_quantization remains as a backwards-compatibility shim that re-exports the same symbols, so existing code such as from flashinfer.fp4_quantization import fp4_quantize keeps working. New code should import from flashinfer.quantization.fp4_quantization (or its canonical re-export at flashinfer.quantization).

This page intentionally does not re-document the FP4 symbols, because each symbol is the same Python object as the one rendered on flashinfer.quantization — duplicating the autosummary entries here would make Sphinx emit “duplicate object description” warnings under sphinx -W.

See Also

• flashinfer.quantization — canonical FP4 / FP8 / packbits API reference, including all of the following symbols that flashinfer.fp4_quantization used to host:

  • flashinfer.quantization.fp4_quantize()

  • flashinfer.quantization.nvfp4_quantize()

  • flashinfer.quantization.nvfp4_batched_quantize()

  • flashinfer.quantization.block_scale_interleave() (alias: nvfp4_block_scale_interleave)

  • flashinfer.quantization.e2m1_and_ufp8sf_scale_to_float()

  • flashinfer.quantization.scaled_fp4_grouped_quantize()

  • flashinfer.quantization.shuffle_matrix_a()

  • flashinfer.quantization.shuffle_matrix_sf_a()

  • flashinfer.quantization.nvfp4_kv_quantize()

  • flashinfer.quantization.nvfp4_kv_dequantize()

  • flashinfer.quantization.nvfp4_quantize_paged_kv_cache()

  • flashinfer.quantization.SfLayout