Merge remote-tracking branch 'origin/master' into cuda-releases

Author: Olivier Chafik

examples/server/public/index.html.gz

@@ -111,12 +111,12 @@ const VueMarkdown = defineComponent(
       highlight: function (str, lang) { // Add highlight.js
         if (lang && hljs.getLanguage(lang)) {
           try {
-            return '<pre><code class="hljs">' +
+            return '<pre dir="auto"><code class="hljs">' +
                    hljs.highlight(str, { language: lang, ignoreIllegals: true }).value +
                    '</code></pre>';
           } catch (__) {}
         }
-        return '<pre><code class="hljs">' + md.value.utils.escapeHtml(str) + '</code></pre>';
+        return '<pre dir="auto"><code class="hljs">' + md.value.utils.escapeHtml(str) + '</code></pre>';
       }
     }));
     // support latex with double dollar sign and square brackets

examples/server/webui/src/main.js

@@ -73,6 +73,7 @@ while read c; do
         src/ggml*.h \
         src/ggml*.c \
         src/ggml*.cpp \
+        src/gguf*.cpp \
         src/ggml-blas/* \
         src/ggml-cann/* \
         src/ggml-cpu/* \
@@ -81,10 +82,12 @@ while read c; do
         src/ggml-kompute/* \
         src/ggml-metal/* \
         src/ggml-musa/* \
+        src/ggml-opencl/* \
         src/ggml-rpc/* \
         src/ggml-sycl/* \
         src/ggml-vulkan/* \
         include/ggml*.h \
+        include/gguf*.h \
         tests/test-opt.cpp \
         tests/test-quantize-fns.cpp \
         tests/test-quantize-perf.cpp \
@@ -123,6 +126,7 @@ if [ -f $SRC_LLAMA/ggml-src.patch ]; then
     # src/ggml*.c          -> ggml/src/ggml*.c
     # src/ggml*.cpp        -> ggml/src/ggml*.cpp
     # src/ggml*.h          -> ggml/src/ggml*.h
+    # src/gguf*.cpp        -> ggml/src/gguf*.cpp
     # src/ggml-blas/*      -> ggml/src/ggml-blas/*
     # src/ggml-cann/*      -> ggml/src/ggml-cann/*
     # src/ggml-cpu/*       -> ggml/src/ggml-cpu/*
@@ -131,11 +135,13 @@ if [ -f $SRC_LLAMA/ggml-src.patch ]; then
     # src/ggml-kompute/*   -> ggml/src/ggml-kompute/*
     # src/ggml-metal/*     -> ggml/src/ggml-metal/*
     # src/ggml-musa/*      -> ggml/src/ggml-musa/*
+    # src/ggml-opencl/*    -> ggml/src/ggml-opencl/*
     # src/ggml-rpc/*       -> ggml/src/ggml-rpc/*
     # src/ggml-sycl/*      -> ggml/src/ggml-sycl/*
     # src/ggml-vulkan/*    -> ggml/src/ggml-vulkan/*
     #
     # include/ggml*.h -> ggml/include/ggml*.h
+    # include/gguf*.h -> ggml/include/gguf*.h
     #
     # tests/test*.cpp -> tests/
     #
@@ -149,18 +155,20 @@ if [ -f $SRC_LLAMA/ggml-src.patch ]; then
         -e 's/([[:space:]]|[ab]\/)src\/ggml(.*)\.c/\1ggml\/src\/ggml\2.c/g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml(.*)\.cpp/\1ggml\/src\/ggml\2.cpp/g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml(.*)\.h/\1ggml\/src\/ggml\2.h/g' \
+        -e 's/([[:space:]]|[ab]\/)src\/gguf(.*)\.cpp/\1ggml\/src\/gguf\2.cpp/g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-blas\//\1ggml\/src\/ggml-blas\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-cann\//\1ggml\/src\/ggml-cann\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-cpu\//\1ggml\/src\/ggml-cpu\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-cuda\//\1ggml\/src\/ggml-cuda\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-hip\//\1ggml\/src\/ggml-hip\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-kompute\//\1ggml\/src\/ggml-kompute\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-metal\//\1ggml\/src\/ggml-metal\//g' \
-        -e 's/([[:space:]]|[ab]\/)src\/ggml-musa\//\1ggml\/src\/ggml-musa\//g' \
+        -e 's/([[:space:]]|[ab]\/)src\/ggml-opencl\//\1ggml\/src\/ggml-opencl\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-rpc\//\1ggml\/src\/ggml-rpc\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-sycl\//\1ggml\/src\/ggml-sycl\//g' \
         -e 's/([[:space:]]|[ab]\/)src\/ggml-vulkan\//\1ggml\/src\/ggml-vulkan\//g' \
         -e 's/([[:space:]]|[ab]\/)include\/ggml(.*)\.h/\1ggml\/include\/ggml\2.h/g' \
+        -e 's/([[:space:]]|[ab]\/)include\/gguf(.*)\.h/\1ggml\/include\/gguf\2.h/g' \
         -e 's/([[:space:]]|[ab]\/)tests\/(.*)\.cpp/\1tests\/\2.cpp/g' \
         -e 's/([[:space:]]|[ab]\/)LICENSE/\1LICENSE/g' \
         -e 's/([[:space:]]|[ab]\/)scripts\/gen-authors\.sh/\1scripts\/gen-authors.sh/g' \

scripts/sync-ggml-am.sh

@@ -1 +1 @@
-c8bd0fee71dc8328d93be301bbee06bc10d30429
+d92321c0d151fe73a47d89738c7c3091ac904297

scripts/sync-ggml.last

@@ -7,6 +7,7 @@ cp -rpv ../ggml/cmake/FindSIMD.cmake ./ggml/cmake/FindSIMD.cmake
 cp -rpv ../ggml/src/ggml*.c        ./ggml/src/
 cp -rpv ../ggml/src/ggml*.cpp      ./ggml/src/
 cp -rpv ../ggml/src/ggml*.h        ./ggml/src/
+cp -rpv ../ggml/src/gguf*.cpp      ./ggml/src/
 cp -rpv ../ggml/src/ggml-blas/*    ./ggml/src/ggml-blas/
 cp -rpv ../ggml/src/ggml-cann/*    ./ggml/src/ggml-cann/
 cp -rpv ../ggml/src/ggml-cpu/*     ./ggml/src/ggml-cpu/
@@ -15,11 +16,13 @@ cp -rpv ../ggml/src/ggml-hip/*     ./ggml/src/ggml-hip/
 cp -rpv ../ggml/src/ggml-kompute/* ./ggml/src/ggml-kompute/
 cp -rpv ../ggml/src/ggml-metal/*   ./ggml/src/ggml-metal/
 cp -rpv ../ggml/src/ggml-musa/*    ./ggml/src/ggml-musa/
+cp -rpv ../ggml/src/ggml-opencl/*  ./ggml/src/ggml-opencl/
 cp -rpv ../ggml/src/ggml-rpc/*     ./ggml/src/ggml-rpc/
 cp -rpv ../ggml/src/ggml-sycl/*    ./ggml/src/ggml-sycl/
 cp -rpv ../ggml/src/ggml-vulkan/*  ./ggml/src/ggml-vulkan/
 
 cp -rpv ../ggml/include/ggml*.h ./ggml/include/
+cp -rpv ../ggml/include/gguf*.h ./ggml/include/
 
 cp -rpv ../ggml/tests/test-opt.cpp           ./tests/test-opt.cpp
 cp -rpv ../ggml/tests/test-quantize-fns.cpp  ./tests/test-quantize-fns.cpp

scripts/sync-ggml.sh

@@ -1356,8 +1356,9 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
 
             // read vocab size from metadata
             uint32_t n_tokens = 0;
-            if (!ml.get_key(LLM_KV_VOCAB_SIZE, n_tokens, false)) {
-                LLAMA_LOG_WARN("%s: there is no vocab_size in metadata\n", __func__);
+            if (ml.get_key(LLM_KV_VOCAB_SIZE, n_tokens, false)) {
+                LLAMA_LOG_WARN("%s: adding %u dummy tokens\n", __func__, n_tokens);
+                id_to_token.resize(n_tokens);
             }
 
             return;