Open Models Almanac
Methodsinference & servingKV cache management

filed under inference & serving

HiCache

Named as an optimized serving configuration, but the evidence does not establish its cache mechanism.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See KV cache management for the methods filed beside it.

sources
2
model
1
labs adopt it
0
strongest
mentioned

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
mentioned 2

Step-5-Preview

StepFundiscussed2 sources

For more optimized configurations, including MegaMoE, attention data parallelism, and HiCache, see the [SGLang Cookbook for Step 5 Preview]

mentionedinference servingin Step 5 PreviewStepFun
1 more from this model

For more optimized configurations, including MegaMoE, attention data parallelism and HiCache, see the SGLang Cookbook for Step 5 Preview.

mentionedinference servingin Step 5 PreviewStepFun
↑