Splash 1.3.0 cuts local agent first-token latency from 19s to 1s via SSD offloading

Splash 1.3.0 introduces SSD offloading, reducing first-token latency from 19 seconds to 1 second when switching back to projects, greatly improving local agent responsiveness.

2026-10-08 ~ 2026-10-09 · 2 related posts

• Splash 1.3.0 cuts local agent first-token time from 19s to 1s via SSD offloading — songhan_mit · 2026-10-08
• Splash 1.3.0 cuts local agent first-token latency from 19s to 1s via SSD offloading on M6 Mac — BeidiChen · 2026-10-09