vrr/BigMoeOnEdge
2
0
Fork 0
mirror of https://github.com/Helldez/BigMoeOnEdge.git synced 2026-10-03 03:25:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(android): add 3 and 2 to the active-experts (top-k) dropdown

Browse source 
The gpt-oss family routes top-4 by default, so 4/3/2 give a useful
speed/quality sweep on it (and 2/3 on the wider Qwen/Gemma widths).
Adds 3 and 2 to N_EXPERT_CHOICES; the override flows through the existing
--n-expert-used kv_override, valid in both streaming and mmap mode.
This commit is contained in:
Helldez 2026-07-13 20:13:32 +02:00
parent dde8887b23
commit e732d22aa3
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/android/app/src/main/java/io/bigmoeonedge/example/AppSettings.kt
View file

@ -103,8 +103,8 @@ data class AppSettings(
// memory pressure on devices where free RAM is tight.
val CACHE_CEIL_CHOICES = intArrayOf(0, 2000, 3000, 4000, 5000, 6000)
val IO_CHOICES = intArrayOf(1, 2, 4, 8)
// 0 = model default (top-k as trained). 6/4 trade output quality for tok/s (fewer routed experts).
val N_EXPERT_CHOICES = intArrayOf(0, 6, 4)
// 0 = model default (top-k as trained). 6/4/3/2 trade output quality for tok/s (fewer routed experts).
val N_EXPERT_CHOICES = intArrayOf(0, 6, 4, 3, 2)
val PREFETCH_CHOICES = intArrayOf(0, 1, 2, 4)
val THREAD_CHOICES = intArrayOf(2, 4, 6, 8)
val NPREDICT_CHOICES = intArrayOf(16, 32, 48, 64, 128, 256, 512, 1024, 2048)