Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.ecrc
#	CMakePresets.json
#	ci/run.sh
#	docs/backend/SYCL.md
#	ggml/src/CMakeLists.txt
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-sampling.cpp

examples/llava/clip.cpp

@@ -219,13 +219,19 @@ static std::string gguf_data_to_str(enum gguf_type type, const void * data, int
 
 static void replace_all(std::string & s, const std::string & search, const std::string & replace) {
     if (search.empty()) {
-        return; // Avoid infinite loop if 'search' is an empty string
+        return;
     }
+    std::string builder;
+    builder.reserve(s.length());
     size_t pos = 0;
-    while ((pos = s.find(search, pos)) != std::string::npos) {
-        s.replace(pos, search.length(), replace);
-        pos += replace.length();
+    size_t last_pos = 0;
+    while ((pos = s.find(search, last_pos)) != std::string::npos) {
+        builder.append(s, last_pos, pos - last_pos);
+        builder.append(replace);
+        last_pos = pos + search.length();
     }
+    builder.append(s, last_pos, std::string::npos);
+    s = std::move(builder);
 }
 
 static std::string gguf_kv_to_str(const struct gguf_context * ctx_gguf, int i) {

examples/quantize/quantize.cpp

@@ -105,7 +105,7 @@ static void usage(const char * executable) {
     printf("  --exclude-weights tensor_name: use importance matrix for this/these tensor(s)\n");
     printf("  --output-tensor-type ggml_type: use this ggml_type for the output.weight tensor\n");
     printf("  --token-embedding-type ggml_type: use this ggml_type for the token embeddings tensor\n");
-    printf("  --keep-split: will generate quatized model in the same shards as input");
+    printf("  --keep-split: will generate quantized model in the same shards as input\n");
     printf("  --override-kv KEY=TYPE:VALUE\n");
     printf("      Advanced option to override model metadata by key in the quantized model. May be specified multiple times.\n");
     printf("Note: --include-weights and --exclude-weights cannot be used together\n");

examples/server/README.md

@@ -247,6 +247,25 @@ logging:
          --log-append             Don't truncate the old log file.
 ```
 
+Available environment variables (if specified, these variables will override parameters specified in arguments):
+
+- `LLAMA_CACHE` (cache directory, used by `--hf-repo`)
+- `HF_TOKEN` (Hugging Face access token, used when accessing a gated model with `--hf-repo`)
+- `LLAMA_ARG_MODEL`
+- `LLAMA_ARG_THREADS`
+- `LLAMA_ARG_CTX_SIZE`
+- `LLAMA_ARG_N_PARALLEL`
+- `LLAMA_ARG_BATCH`
+- `LLAMA_ARG_UBATCH`
+- `LLAMA_ARG_N_GPU_LAYERS`
+- `LLAMA_ARG_THREADS_HTTP`
+- `LLAMA_ARG_CHAT_TEMPLATE`
+- `LLAMA_ARG_N_PREDICT`
+- `LLAMA_ARG_ENDPOINT_METRICS`
+- `LLAMA_ARG_ENDPOINT_SLOTS`
+- `LLAMA_ARG_EMBEDDINGS`
+- `LLAMA_ARG_FLASH_ATTN`
+- `LLAMA_ARG_DEFRAG_THOLD`
 
 ## Build
 

examples/server/server.cpp

@@ -2508,6 +2508,9 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
+    // parse arguments from environment variables
+    gpt_params_parse_from_env(params);
+
     // TODO: not great to use extern vars
     server_log_json = params.log_json;
     server_verbose = params.verbosity > 0;