From: Georgi Gerganov <redacted>
Date: Wed, 3 Apr 2024 13:11:15 +0000 (+0300)
Subject: readme : update hot topics
X-Git-Tag: upstream/0.0.4488~1899
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=076b08649ecc3b0e1c0709c2a086a63eddd1bf32;p=pkg%2Fggml%2Fsources%2Fllama.cpp

readme : update hot topics
---

diff --git a/README.md b/README.md
index 1207763f..affd0b81 100644
--- a/README.md
+++ b/README.md
@@ -18,6 +18,7 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)
 
 ### Hot topics
 
+- **MoE memory layout has been updated - reconvert models for `mmap` support and regenerate `imatrix` https://github.com/ggerganov/llama.cpp/pull/6387**
 - Model sharding instructions using `gguf-split` https://github.com/ggerganov/llama.cpp/discussions/6404
 - Fix major bug in Metal batched inference https://github.com/ggerganov/llama.cpp/pull/6225
 - Multi-GPU pipeline parallelizm support https://github.com/ggerganov/llama.cpp/pull/6017