Merge pull request #3343 from dhiltgen/bump_more2

Bump llama.cpp to b2581

.github/workflows/test.yaml

@@ -260,7 +260,9 @@ jobs:
           mkdir -p llm/build/windows/$ARCH/stub/stub/bin/
           touch llm/build/windows/$ARCH/stub/stub/bin/stub.dll
         if: ${{ startsWith(matrix.os, 'windows-') }}
-      - uses: golangci/golangci-lint-action@v3
+      - uses: golangci/golangci-lint-action@v4
+        with:
+          args: --timeout 8m0s
   test:
     strategy:
       matrix:

llm/llama.cpp

@@ -1 +1 @@
-Subproject commit ad3a0505e3b6cd777259ee35e61d428357ffc565
+Subproject commit 37e7854c104301c5b5323ccc40e07699f3a62c3e

llm/patches/04-locale.diff

@@ -1,13 +0,0 @@
-diff --git a/llama.cpp b/llama.cpp
-index b27aa272..99372f9c 100644
---- a/llama.cpp
-+++ b/llama.cpp
-@@ -9360,7 +9360,7 @@ struct llm_tokenizer_wpm {
-     }
- 
-     uint32_t to_lower(uint32_t code) {
--        static const std::locale locale("en_US.UTF-8");
-+        static const std::locale locale("");
- #if defined(_WIN32)
-         if (code > 0xFFFF) {
-             return code;