Read the equation
Using the conventional count of one multiplication plus one addition per multiply–accumulate,36.52 GMAC corresponds to 73.04 GFLOP, rounded to 73.0. This is arithmetic applied to the dossier’s operation estimate, not a measured throughput rate. Attention work varies with sequence length and the chosen implementation.
Terms & definitions
The recovered passage does not supply a separate symbol table. Read the source context for the notation used in this version; familiar letters may carry different meanings in other builds.
How it works
Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.
Assumptions & limits
Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.
Original context
Read the surrounding source passage
dense MLP (3 layers) 1.19 GMAC 3.3%
lm_head 0.93 GMAC 2.5%
---------------------------------------------------------------------------
TOTAL 36.52 GMAC = 73.0 GFLOP per token
---------------------------------------------------------------------------
On 12 threads of AVX2 without VNNI, roughly 150 GOPS sustained int8 is
realistic for this CPU: about 0.24 s per token of arithmetic.Exact original notation
TOTAL 36.52 GMAC = 73.0 GFLOP per token