From 018af37b8a9542bae26be7b8b8b83e67b1ccaa6c Mon Sep 17 00:00:00 2001
From: eyonce <119352785+eyonce@users.noreply.github.com>
Date: Thu, 23 Jul 2026 16:44:52 +0000
Subject: [PATCH] perf(llama32_1b): pin Q8 prefill and decode runtime

---
 .gitmodules                                 | 2 +-
 ported_models/llama_cpp_et/src/llama.cpp-et | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.gitmodules b/.gitmodules
index 19dae82b..79f36260 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,3 +1,3 @@
 [submodule "ported_models/llama_cpp_et/src/llama.cpp-et"]
 	path = ported_models/llama_cpp_et/src/llama.cpp-et
-	url = https://github.com/aifoundry-org/llama.cpp.git
+	url = https://github.com/eyonce/llama.cpp.git
diff --git a/ported_models/llama_cpp_et/src/llama.cpp-et b/ported_models/llama_cpp_et/src/llama.cpp-et
index f67c2b2a..7b0a32a6 160000
--- a/ported_models/llama_cpp_et/src/llama.cpp-et
+++ b/ported_models/llama_cpp_et/src/llama.cpp-et
@@ -1 +1 @@
-Subproject commit f67c2b2a30a24bf9354857cde0f233620a20eb23
+Subproject commit 7b0a32a63719b4da312f8c28c5a3ebc656bbb970