Can these REAP models be run with TensorRT-LLM?
#4 opened about 1 month ago
by
mAlyy0
Request: Step-3.5-Flash REAP variant with ~40% pruning
➕ 4
4
#3 opened about 1 month ago
by
rodrigomt
nvfp4
➕👍 2
1
#1 opened about 1 month ago
by
ktsaou