Merge branch 'upstream' into concedo_experimental

# Conflicts: # .github/workflows/check-vendor.yml # .github/workflows/close-issue.yml # .github/workflows/editorconfig.yml # .github/workflows/gguf-publish.yml # .github/workflows/labeler.yml # .github/workflows/pre-tokenizer-hashes.yml # .github/workflows/python-check-requirements.yml # .github/workflows/python-lint.yml # .github/workflows/python-type-check.yml # .github/workflows/server.yml # .github/workflows/update-ops-docs.yml # README.md # docs/build.md # examples/model-conversion/scripts/utils/perplexity-gen.sh # examples/model-conversion/scripts/utils/perplexity-run-simple.sh # examples/model-conversion/scripts/utils/perplexity-run.sh # examples/model-conversion/scripts/utils/quantize.sh # examples/model-conversion/scripts/utils/run-embedding-server.sh # ggml/src/ggml-cpu/ggml-cpu.c # ggml/src/ggml-hexagon/htp/flash-attn-ops.c # ggml/src/ggml-opencl/CMakeLists.txt # ggml/src/ggml-opencl/ggml-opencl.cpp # ggml/src/ggml-opencl/kernels/cvt.cl # ggml/src/ggml-opencl/kernels/mul_mv_q6_k_f32.cl # ggml/src/ggml-sycl/ggml-sycl.cpp # scripts/compare-llama-bench.py # tests/test-backend-ops.cpp # tests/test-gguf.cpp # tools/cli/README.md # tools/completion/README.md # tools/server/README.md
2026-09-18 16:55:14 +02:00 · 2026-01-27 23:06:13 +08:00
parent 3a84623ea5 68ac3acb43
commit f6ece6fd37
40 changed files with 3108 additions and 477 deletions
@@ -334,8 +334,12 @@ static void llama_params_fit_impl(
                            __func__, hp_nct, cparams->n_ctx, memory_reduction/MiB);
                    }
                } else {
-                    LLAMA_LOG_INFO("%s: default model context size is %" PRIu32 " which is <= the min. context size of %" PRIu32 " -> no change\n",
-                        __func__, hp_nct, n_ctx_min);
+                    if (n_ctx_min == UINT32_MAX) {
+                        LLAMA_LOG_INFO("%s: user has requested full context size of %" PRIu32 " -> no change\n", __func__, hp_nct);
+                    } else {
+                        LLAMA_LOG_INFO("%s: default model context size is %" PRIu32 " which is <= the min. context size of %" PRIu32 " -> no change\n",
+                            __func__, hp_nct, n_ctx_min);
+                    }
                }
            } else {
                LLAMA_LOG_INFO("%s: context size set by user to %" PRIu32 " -> no change\n", __func__, cparams->n_ctx);
@@ -1114,25 +1118,55 @@ int32_t llama_chat_apply_template(
 // model split
 //

-int llama_split_path(char * split_path, size_t maxlen, const char * path_prefix, int split_no, int split_count) {
+int32_t llama_split_path(
+    char * split_path,
+    size_t maxlen,
+    const char * path_prefix,
+    int32_t split_no,
+    int32_t split_count) {
+
    static const char * const SPLIT_PATH_FORMAT = "%s-%05d-of-%05d.gguf";
-    if (snprintf(split_path, maxlen, SPLIT_PATH_FORMAT, path_prefix, split_no + 1, split_count)) {
-        return strlen(split_path);
+
+    const int written = snprintf(
+        split_path,
+        maxlen,
+        SPLIT_PATH_FORMAT,
+        path_prefix,
+        split_no + 1,
+        split_count
+    );
+
+    if (written < 0 || (size_t) written >= maxlen) {
+        return 0;
    }
-    return 0;
+
+    return (int32_t) written;
 }

-int llama_split_prefix(char * split_prefix, size_t maxlen, const char * split_path, int split_no, int split_count) {
-    std::string str_split_path(split_path);
-    char postfix[32];
-    snprintf(postfix, 32, "-%05d-of-%05d.gguf", split_no + 1, split_count);
-    std::string str_postfix(postfix);
+int32_t llama_split_prefix(
+    char * split_prefix,
+    size_t maxlen,
+    const char * split_path,
+    int32_t split_no,
+    int32_t split_count) {

-    // check if split_prefix ends with postfix
-    int size_prefix = str_split_path.size() - str_postfix.size();
-    if (size_prefix > 0 && str_split_path.find(str_postfix, size_prefix) != std::string::npos) {
-        snprintf(split_prefix, std::min((size_t) size_prefix + 1, maxlen), "%s", split_path);
-        return size_prefix;
+    const std::string str_split_path(split_path);
+
+    char postfix[32];
+    snprintf(postfix, sizeof(postfix), "-%05d-of-%05d.gguf", split_no + 1, split_count);
+
+    const std::string str_postfix(postfix);
+    if (str_split_path.size() <= str_postfix.size()) {
+        return 0;
+    }
+
+    const size_t size_prefix = str_split_path.size() - str_postfix.size();
+
+    if (str_split_path.compare(size_prefix, std::string::npos, str_postfix) == 0) {
+        const size_t copy_len = std::min(size_prefix + 1, maxlen);
+        snprintf(split_prefix, copy_len, "%s", split_path);
+
+        return (int32_t) size_prefix;
    }

    return 0;