Claude
a429aa40f6
Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Cfo2K4u4rF18QsPXPFnytf
11 lines
602 B
Plaintext
11 lines
602 B
Plaintext
# Time to rerank N candidates (median and slowest of 12 calls, after 3 warm-up calls)
|
|
|
|
machine: 2 vCPU, JDK 25.0.5
|
|
fp32 cross-encoder, max length 256 tokens; the first column of each cell is the median in ms, the second the slowest
|
|
|
|
candidates batch 1 batch 8 batch 32 batch 32, 1 thread
|
|
10 125 / 188 121 / 142 122 / 138 148 / 208
|
|
20 205 / 226 195 / 220 220 / 257 322 / 411
|
|
50 546 / 661 512 / 578 489 / 549 800 / 913
|
|
94 897 / 1062 838 / 966 962 / 1075 1635 / 1928
|