Closing Looping’s Inference-Memory Gap via KV-Sharing
AI & ML interests
None defined yet.
Recent Activity
models 9
SandyResearch/benice-1.3b
Updated • 53
SandyResearch/benice-770m
Updated • 46
SandyResearch/benice-140m
Updated • 59
SandyResearch/benice-370m
Updated • 41
SandyResearch/parcae-1.3b
Text Generation • Updated • 502 • 8
SandyResearch/parcae-770m
Text Generation • Updated • 178 • 4
SandyResearch/parcae-370m
Text Generation • Updated • 267 • 3
SandyResearch/parcae-140m
Text Generation • Updated • 1.06k • 3
SandyResearch/parcae-tokenizer
Updated