Deploy audited RTX 6000D Flash-Next 128K multimodal baseline

This commit is contained in:
2026-09-18 10:47:26 +08:00
commit 7e53821920
45 changed files with 1745 additions and 0 deletions
+12
View File
@@ -0,0 +1,12 @@
{
"eager": {
"median_decode_tps": 22.001705837292434,
"median_ttft_s": 0.11141436400066596
},
"graph": {
"median_decode_tps": 77.11544284916513,
"median_ttft_s": 0.06954390600003535
},
"speedup": 3.5049756332282227,
"identical_generated_text": true
}