Tying the two scales of a ternary weight decomposition at ratio 3 yields a uniform nine-level quantizer whose folded 4-bit format matches a 4.5-bit baseline on measured fidelity while decoding faster.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving
Tying the two scales of a ternary weight decomposition at ratio 3 yields a uniform nine-level quantizer whose folded 4-bit format matches a 4.5-bit baseline on measured fidelity while decoding faster.