llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)

llama/llama.cpp/src/unicode.cpp

@@ -12,18 +12,17 @@
 
 #include <algorithm>
 #include <cassert>
+#include <codecvt>
 #include <cstddef>
 #include <cstdint>
+#include <locale>
 #include <map>
 #include <regex>
 #include <stdexcept>
 #include <string>
 #include <unordered_map>
-#include <unordered_set>
 #include <utility>
 #include <vector>
-#include <locale>
-#include <codecvt>
 
 size_t unicode_len_utf8(char src) {
     const size_t lookup[] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 3, 4 };
@@ -641,8 +640,15 @@ std::vector<uint32_t> unicode_cpts_from_utf8(const std::string & utf8) {
     result.reserve(utf8.size());
     size_t offset = 0;
     while (offset < utf8.size()) {
+        try {
             result.push_back(unicode_cpt_from_utf8(utf8, offset));
         }
+        catch (const std::invalid_argument & /*ex*/) {
+            // Silently ignore invalid UTF-8 input to avoid leaking the exception beyond llama_tokenize
+            ++offset;
+            result.emplace_back(0xFFFD); // replacement character
+        }
+    }
     return result;
 }
 
@@ -724,7 +730,7 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
     const auto cpts = unicode_cpts_from_utf8(text);
 
     // generate a "collapsed" representation of the text, where all codepoints are replaced by a single byte
-    // ref: https://github.com/ggerganov/llama.cpp/pull/6920#issuecomment-2081479935
+    // ref: https://github.com/ggml-org/llama.cpp/pull/6920#issuecomment-2081479935
     std::string text_collapsed;
     if (need_collapse) {
         // collapse all unicode categories

llama/mllama.cpp

@@ -5,6 +5,7 @@
 #include "ggml-backend.h"
 #include "ggml-cpu.h"
 #include "ggml.h"
+#include "gguf.h"
 
 #ifdef GGML_USE_CUDA
 #include "ggml-cuda.h"

llama/patches/0006-conditional-fattn.patch

@@ -8,10 +8,10 @@ Subject: [PATCH] conditional-fattn
  1 file changed, 2 insertions(+)
 
 diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
-index be29e979..aaa79ea4 100644
+index b094929b..36165840 100644
 --- a/ggml/src/ggml-cuda/ggml-cuda.cu
 +++ b/ggml/src/ggml-cuda/ggml-cuda.cu
-@@ -2159,9 +2159,11 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
+@@ -2282,9 +2282,11 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
          case GGML_OP_ARGSORT:
              ggml_cuda_op_argsort(ctx, dst);
              break;

llama/patches/0014-sort-devices-by-score.patch → llama/patches/0013-sort-devices-by-score.patch

@@ -8,7 +8,7 @@ Subject: [PATCH] sort devices by score
  1 file changed, 13 insertions(+), 8 deletions(-)
 
 diff --git a/ggml/src/ggml-backend-reg.cpp b/ggml/src/ggml-backend-reg.cpp
-index 899d16f2..135f7df0 100644
+index 95036ef8..98d5e14d 100644
 --- a/ggml/src/ggml-backend-reg.cpp
 +++ b/ggml/src/ggml-backend-reg.cpp
 @@ -150,7 +150,7 @@ struct ggml_backend_reg_entry {