APIUp to 25% cheaper than official pricesTry the API →
HermesHermes Agent Docs
API
Back to News
newsInfraOpen Source

Inco AI's Splash 1.3.0 Cuts Mac Prefill Wait by 1.49x for Coding Agents

Splash 1.3.0 cuts time to first token on local Macs by offloading KV cache to SSD and splitting prefill between the GPU and Neural Engine.

Inco AI's Splash 1.3.0 Cuts Mac Prefill Wait by 1.49x for Coding Agents
Source
Inco AI
Published
Author
AlphaSignal Newsroom
Read
1 min read

Splash 1.3.0 cuts time to first token on local Macs by offloading KV cache to SSD and splitting prefill between the GPU and Neural Engine.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

vLLM 0.31 Speeds Up DeepSeek and Slashes Engine Restart Times
vLLM · news

vLLM 0.31 Speeds Up DeepSeek and Slashes Engine Restart Times

vLLM's Vela 2.0 Collapses Nine AI Safety Checks Into One Open Model
vLLM · news

vLLM's Vela 2.0 Collapses Nine AI Safety Checks Into One Open Model

Ollaya Runs Decision Models Locally With Millisecond Structured Outputs
AlphaSignal · repo

Ollaya Runs Decision Models Locally With Millisecond Structured Outputs