forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 16
MoE Cache Drafting
Rocco A edited this page Sep 14, 2026
·
9 revisions
Do not use the retired moe-cache-drafting branch. Build moe-cache instead.
Use:
git clone --branch moe-cache https://github.com/GenerelSchwerz/llama.cpp.gitmoe-cache now carries target caching, grouped verification, separate-model drafting, integrated MTP, retained state, graph variants, overlap, and prefetch. Experimental features remain opt-in.
Use old commit links only for historical evidence. Use moe-cache at 925933801 or newer for current behavior.
MoE Cache overview - MoE Cache flags and setup - Grouped MoE drafting - Feature index
GenerelSchwerz llama.cpp
- Home
- Discord community
- Complete feature index
- Hardware setup guides
- Owner-verified evidence
- Notable runs
- Benchmark comparison showcase
- BeeLlama Main
- Llama Main
- Llama Dev
- MoE Cache
Feature groups
- Memory placement and workspace
- Validation and diagnostics
- CUDA MoE cache and helpers
- Grouped MoE drafting
Source branches