Model techniques map
Techniquessoftware implementationkernel & quantization library

implementation detail · filed under software implementation

CUTLASS

A GPU kernel backend option identified as CUTLASS.

source
1
model
1
lab adopt it
1
strongest
optional

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

VLLM_FLASHINFER_MOE_BACKEND=throughput(CUTLASS)

optionalsoftware implementationin Nemotron 3 UltraNVIDIA

Filed alongside

Other methods under software implementation :: kernel & quantization library.