Skip to content

[NVIDIA] Add Low Latency NVFP4 decode kernels from Flashinfer#8552

Merged
zhyncs merged 6 commits intomainfrom
low_latency_nvfp4_decode
Aug 4, 2025
Merged

[NVIDIA] Add Low Latency NVFP4 decode kernels from Flashinfer#8552
zhyncs merged 6 commits intomainfrom
low_latency_nvfp4_decode

Commits

Commits on Aug 4, 2025