Alexander Korolev b1f054231b beam lane: 384K context (13.6x concurrency) + needle-in-haystack at 131K and 327K tokens (both correct, 60s/175s TTFT) há 1 semana atrás
..
reports 502080b104 beam lane: depth sweep (31-35 tok/s to 128K) + the second/third quality runs (92/100, Hard Mode 95%) há 1 semana atrás
NOTE.md b1f054231b beam lane: 384K context (13.6x concurrency) + needle-in-haystack at 131K and 327K tokens (both correct, 60s/175s TTFT) há 1 semana atrás
recipe.toml b1f054231b beam lane: 384K context (13.6x concurrency) + needle-in-haystack at 131K and 327K tokens (both correct, 60s/175s TTFT) há 1 semana atrás