Ssignal
17
·13 hr ago·1 signals
Archived topic · source no longer tracked
I reverse-engineered an NPU vendor's engine format (int8 weights stored as two nibble planes) to run GGUFs with no model conversion — now 1.5× faster than the vendor's own runtime
Model release
Heat trend
New
The percentage is based on available heat signal, not comment count or independent people.