common : skip model validation when --completion-bash is requested (#17975)

* model-conversion : use CONVERTED_MODEL value for converted model [no ci]

This commit updates the model verification scripts to use the
CONVERTED_MODEL environment variable instead of using the MODEL_PATH
(the original model path) as the basis for the converted model file
name.

The motivation for this that currently if the converted model file name
differs from the original model directory/name the verification scripts
will look for the wrong .bin files that were generating when running the
models.
For example, the following steps were not possible:
```console
(venv) $ huggingface-cli download google/gemma-3-270m-it --local-dir ggml-org/gemma-3-270m
(venv) $ python3 convert_hf_to_gguf.py ggml-org/gemma-3-270m --outfile test-bf16.gguf --outtype bf16
(venv) $ cd examples/model-conversion/
(venv) $ export MODEL_PATH=../../ggml-org/gemma-3-270m
(venv) $ export CONVERTED_MODEL=../../test-bf16.gguf
(venv) $ make causal-verify-logits
...
Data saved to data/llamacpp-test-bf16.bin
Data saved to data/llamacpp-test-bf16.txt
Error: llama.cpp logits file not found: data/llamacpp-gemma-3-270m.bin
Please run scripts/run-converted-model.sh first to generate this file.
make: *** [Makefile:62: causal-verify-logits] Error 1
```

With the changes in this commit, the above steps will now work as
expected.

common/arg.cpp

@@ -105,6 +105,16 @@ bool common_arg::is_exclude(enum llama_example ex) {
 
 bool common_arg::get_value_from_env(std::string & output) const {
     if (env == nullptr) return false;
+    if (!args_neg.empty()) {
+        // for compatibility, we need to check LLAMA_ARG_NO_ env as well
+        std::string neg_env = env;
+        string_replace_all(neg_env, "LLAMA_ARG_", "LLAMA_ARG_NO_");
+        char * neg_value = std::getenv(neg_env.c_str());
+        if (neg_value) {
+            output = "0"; // falsey
+            return true;
+        }
+    }
     char * value = std::getenv(env);
     if (value) {
         output = value;
@@ -114,6 +124,14 @@ bool common_arg::get_value_from_env(std::string & output) const {
 }
 
 bool common_arg::has_value_from_env() const {
+    if (env != nullptr && !args_neg.empty()) {
+        // for compatibility, we need to check LLAMA_ARG_NO_ env as well
+        std::string neg_env = env;
+        string_replace_all(neg_env, "LLAMA_ARG_", "LLAMA_ARG_NO_");
+        if (std::getenv(neg_env.c_str())) {
+            return true;
+        }
+    }
     return env != nullptr && std::getenv(env);
 }
 
@@ -151,9 +169,10 @@ std::string common_arg::to_string() const {
     std::string leading_spaces(n_leading_spaces, ' ');
 
     std::ostringstream ss;
-    for (const auto arg : args) {
-        if (arg == args.front()) {
-            if (args.size() == 1) {
+    auto all_args = get_args(); // also contains args_neg
+    for (const auto & arg : all_args) {
+        if (arg == all_args.front()) {
+            if (all_args.size() == 1) {
                 ss << arg;
             } else {
                 // first arg is usually abbreviation, we need padding to make it more beautiful
@@ -162,7 +181,7 @@ std::string common_arg::to_string() const {
                 ss << tmp << spaces;
             }
         } else {
-            ss << arg << (arg != args.back() ? ", " : "");
+            ss << arg << (arg != all_args.back() ? ", " : "");
         }
     }
     if (value_hint) ss << " " << value_hint;
@@ -181,6 +200,31 @@ std::string common_arg::to_string() const {
     return ss.str();
 }
 
+std::vector<std::string> common_arg::get_args() const {
+    std::vector<std::string> result;
+    for (const auto & arg : args) {
+        result.push_back(std::string(arg));
+    }
+    for (const auto & arg : args_neg) {
+        result.push_back(std::string(arg));
+    }
+    return result;
+}
+
+std::vector<std::string> common_arg::get_env() const {
+    std::vector<std::string> result;
+    if (env) {
+        result.push_back(std::string(env));
+    }
+    if (!args_neg.empty() && env) {
+        // for compatibility, we need to add LLAMA_ARG_NO_ variant
+        std::string neg_env = env;
+        string_replace_all(neg_env, "LLAMA_ARG_", "LLAMA_ARG_NO_");
+        result.push_back(neg_env);
+    }
+    return result;
+}
+
 //
 // utils
 //
@@ -316,6 +360,16 @@ static std::string get_all_kv_cache_types() {
     return msg.str();
 }
 
+static bool parse_bool_value(const std::string & value) {
+    if (is_truthy(value)) {
+        return true;
+    } else if (is_falsey(value)) {
+        return false;
+    } else {
+        throw std::invalid_argument("invalid boolean value");
+    }
+}
+
 //
 // CLI argument parsing functions
 //
@@ -323,10 +377,13 @@ static std::string get_all_kv_cache_types() {
 static bool common_params_parse_ex(int argc, char ** argv, common_params_context & ctx_arg) {
     common_params & params = ctx_arg.params;
 
-    std::unordered_map<std::string, common_arg *> arg_to_options;
+    std::unordered_map<std::string, std::pair<common_arg *, bool>> arg_to_options;
     for (auto & opt : ctx_arg.options) {
         for (const auto & arg : opt.args) {
-            arg_to_options[arg] = &opt;
+            arg_to_options[arg] = {&opt, /* is_positive */ true};
+        }
+        for (const auto & arg : opt.args_neg) {
+            arg_to_options[arg] = {&opt, /* is_positive */ false};
         }
     }
 
@@ -335,12 +392,15 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
         std::string value;
         if (opt.get_value_from_env(value)) {
             try {
-                if (opt.handler_void && (value == "1" || value == "true")) {
+                if (opt.handler_void && is_truthy(value)) {
                     opt.handler_void(params);
                 }
                 if (opt.handler_int) {
                     opt.handler_int(params, std::stoi(value));
                 }
+                if (opt.handler_bool) {
+                    opt.handler_bool(params, parse_bool_value(value));
+                }
                 if (opt.handler_string) {
                     opt.handler_string(params, value);
                     continue;
@@ -369,7 +429,9 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
         if (arg_to_options.find(arg) == arg_to_options.end()) {
             throw std::invalid_argument(string_format("error: invalid argument: %s", arg.c_str()));
         }
-        auto opt = *arg_to_options[arg];
+        auto & tmp = arg_to_options[arg];
+        auto opt = *tmp.first;
+        bool is_positive = tmp.second;
         if (opt.has_value_from_env()) {
             fprintf(stderr, "warn: %s environment variable is set, but will be overwritten by command line argument %s\n", opt.env, arg.c_str());
         }
@@ -378,6 +440,10 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
                 opt.handler_void(params);
                 continue;
             }
+            if (opt.handler_bool) {
+                opt.handler_bool(params, is_positive);
+                continue;
+            }
 
             // arg with single value
             check_arg(i);
@@ -402,7 +468,7 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
             throw std::invalid_argument(string_format(
                 "error while handling argument \"%s\": %s\n\n"
                 "usage:\n%s\n\nto show complete usage, run with -h",
-                arg.c_str(), e.what(), arg_to_options[arg]->to_string().c_str()));
+                arg.c_str(), e.what(), opt.to_string().c_str()));
         }
     }
 
@@ -438,7 +504,7 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
 
     // model is required (except for server)
     // TODO @ngxson : maybe show a list of available models in CLI in this case
-    if (params.model.path.empty() && ctx_arg.ex != LLAMA_EXAMPLE_SERVER && !params.usage) {
+    if (params.model.path.empty() && ctx_arg.ex != LLAMA_EXAMPLE_SERVER && !params.usage && !params.completion) {
         throw std::invalid_argument("error: --model is required\n");
     }
 
@@ -573,6 +639,7 @@ static void common_params_print_completion(common_params_context & ctx_arg) {
         "llama-batched-bench",
         "llama-bench",
         "llama-cli",
+        "llama-completion",
         "llama-convert-llama2c-to-ggml",
         "llama-cvector-generator",
         "llama-embedding",
@@ -750,11 +817,11 @@ static std::string list_builtin_chat_templates() {
 }
 
 bool common_arg_utils::is_truthy(const std::string & value) {
-    return value == "on" || value == "enabled" || value == "1";
+    return value == "on" || value == "enabled" || value == "true" || value == "1";
 }
 
 bool common_arg_utils::is_falsey(const std::string & value) {
-    return value == "off" || value == "disabled" || value == "0";
+    return value == "off" || value == "disabled" || value == "false" || value == "0";
 }
 
 bool common_arg_utils::is_autoy(const std::string & value) {
@@ -839,10 +906,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ));
     add_opt(common_arg(
+        {"--display-prompt"},
         {"--no-display-prompt"},
-        string_format("don't print prompt at generation (default: %s)", !params.display_prompt ? "true" : "false"),
-        [](common_params & params) {
-            params.display_prompt = false;
+        string_format("whether to print prompt at generation (default: %s)", params.display_prompt ? "true" : "false"),
+        [](common_params & params, bool value) {
+            params.display_prompt = value;
         }
     ).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}));
     add_opt(common_arg(
@@ -1055,18 +1123,12 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             params.kv_unified = true;
         }
     ).set_env("LLAMA_ARG_KV_UNIFIED"));
-    add_opt(common_arg(
-        {"--no-context-shift"},
-        string_format("disables context shift on infinite text generation (default: %s)", params.ctx_shift ? "disabled" : "enabled"),
-        [](common_params & params) {
-            params.ctx_shift = false;
-        }
-    ).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_NO_CONTEXT_SHIFT"));
     add_opt(common_arg(
         {"--context-shift"},
-        string_format("enables context shift on infinite text generation (default: %s)", params.ctx_shift ? "enabled" : "disabled"),
-        [](common_params & params) {
-            params.ctx_shift = true;
+        {"--no-context-shift"},
+        string_format("whether to use context shift on infinite text generation (default: %s)", params.ctx_shift ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.ctx_shift = value;
         }
     ).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_CONTEXT_SHIFT"));
     add_opt(common_arg(
@@ -1106,20 +1168,22 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_DIFFUSION}));
     add_opt(common_arg(
+        {"--perf"},
         {"--no-perf"},
-        string_format("disable internal libllama performance timings (default: %s)", params.no_perf ? "true" : "false"),
-        [](common_params & params) {
-            params.no_perf = true;
-            params.sampling.no_perf = true;
+        string_format("whether to enable internal libllama performance timings (default: %s)", params.no_perf ? "true" : "false"),
+        [](common_params & params, bool value) {
+            params.no_perf = !value;
+            params.sampling.no_perf = !value;
         }
-    ).set_env("LLAMA_ARG_NO_PERF"));
+    ).set_env("LLAMA_ARG_PERF"));
     add_opt(common_arg(
+        {"--show-timings"},
         {"--no-show-timings"},
-        string_format("disable timing information after each response (default: %s)", params.show_timings ? "true" : "false"),
-        [](common_params & params) {
-            params.show_timings = false;
+        string_format("whether to show timing information after each response (default: %s)", params.show_timings ? "true" : "false"),
+        [](common_params & params, bool value) {
+            params.show_timings = value;
         }
-    ).set_examples({LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_NO_SHOW_TIMINGS"));
+    ).set_examples({LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_SHOW_TIMINGS"));
     add_opt(common_arg(
         {"-f", "--file"}, "FNAME",
         "a file containing the prompt (default: none)",
@@ -1171,16 +1235,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_excludes({LLAMA_EXAMPLE_SERVER}));
     add_opt(common_arg(
         {"-e", "--escape"},
-        string_format("process escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\) (default: %s)", params.escape ? "true" : "false"),
-        [](common_params & params) {
-            params.escape = true;
-        }
-    ));
-    add_opt(common_arg(
         {"--no-escape"},
-        "do not process escape sequences",
-        [](common_params & params) {
-            params.escape = false;
+        string_format("whether to process escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\) (default: %s)", params.escape ? "true" : "false"),
+        [](common_params & params, bool value) {
+            params.escape = value;
         }
     ));
     add_opt(common_arg(
@@ -1227,19 +1285,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER}));
     add_opt(common_arg(
         {"-cnv", "--conversation"},
-        "run in conversation mode:\n"
+        {"-no-cnv", "--no-conversation"},
+        "whether to run in conversation mode:\n"
         "- does not print special tokens and suffix/prefix\n"
         "- interactive mode is also enabled\n"
         "(default: auto enabled if chat template is available)",
-        [](common_params & params) {
-            params.conversation_mode = COMMON_CONVERSATION_MODE_ENABLED;
-        }
-    ).set_examples({LLAMA_EXAMPLE_COMPLETION}));
-    add_opt(common_arg(
-        {"-no-cnv", "--no-conversation"},
-        "force disable conversation mode (default: false)",
-        [](common_params & params) {
-            params.conversation_mode = COMMON_CONVERSATION_MODE_DISABLED;
+        [](common_params & params, bool value) {
+            params.conversation_mode = value ? COMMON_CONVERSATION_MODE_ENABLED : COMMON_CONVERSATION_MODE_DISABLED;
         }
     ).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}));
     add_opt(common_arg(
@@ -1297,10 +1349,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_COMPLETION}));
     add_opt(common_arg(
+        {"--warmup"},
         {"--no-warmup"},
-        "skip warming up the model with an empty run",
-        [](common_params & params) {
-            params.warmup = false;
+        string_format("whether to perform warmup with an empty run (default: %s)", params.warmup ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.warmup = value;
         }
     ).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_MTMD, LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_RETRIEVAL, LLAMA_EXAMPLE_PERPLEXITY}));
     add_opt(common_arg(
@@ -1702,19 +1755,21 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_env("LLAMA_ARG_GRP_ATTN_W").set_examples({LLAMA_EXAMPLE_COMPLETION}));
     add_opt(common_arg(
+        {"-kvo", "--kv-offload"},
         {"-nkvo", "--no-kv-offload"},
-        "disable KV offload",
-        [](common_params & params) {
-            params.no_kv_offload = true;
+        string_format("whether to enable KV cache offloading (default: %s)", params.no_kv_offload ? "disabled" : "enabled"),
+        [](common_params & params, bool value) {
+            params.no_kv_offload = !value;
         }
-    ).set_env("LLAMA_ARG_NO_KV_OFFLOAD"));
+    ).set_env("LLAMA_ARG_KV_OFFLOAD"));
     add_opt(common_arg(
+        {"--repack"},
         {"-nr", "--no-repack"},
-        "disable weight repacking",
-        [](common_params & params) {
-            params.no_extra_bufts = true;
+        string_format("whether to enable weight repacking (default: %s)", params.no_extra_bufts ? "disabled" : "enabled"),
+        [](common_params & params, bool value) {
+            params.no_extra_bufts = !value;
         }
-    ).set_env("LLAMA_ARG_NO_REPACK"));
+    ).set_env("LLAMA_ARG_REPACK"));
     add_opt(common_arg(
         {"--no-host"},
         "bypass host buffer allowing extra buffers to be used",
@@ -1843,18 +1898,12 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_PARALLEL}));
     add_opt(common_arg(
         {"-cb", "--cont-batching"},
-        string_format("enable continuous batching (a.k.a dynamic batching) (default: %s)", params.cont_batching ? "enabled" : "disabled"),
-        [](common_params & params) {
-            params.cont_batching = true;
+        {"-nocb", "--no-cont-batching"},
+        string_format("whether to enable continuous batching (a.k.a dynamic batching) (default: %s)", params.cont_batching ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.cont_batching = value;
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CONT_BATCHING"));
-    add_opt(common_arg(
-        {"-nocb", "--no-cont-batching"},
-        "disable continuous batching",
-        [](common_params & params) {
-            params.cont_batching = false;
-        }
-    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONT_BATCHING"));
     add_opt(common_arg(
         {"-mm", "--mmproj"}, "FILE",
         "path to a multimodal projector file. see tools/mtmd/README.md\n"
@@ -1871,19 +1920,21 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_URL"));
     add_opt(common_arg(
-        {"--no-mmproj"},
-        "explicitly disable multimodal projector, useful when using -hf",
-        [](common_params & params) {
-            params.no_mmproj = true;
+        {"--mmproj-auto"},
+        {"--no-mmproj", "--no-mmproj-auto"},
+        string_format("whether to use multimodal projector file (if available), useful when using -hf (default: %s)", params.no_mmproj ? "disabled" : "enabled"),
+        [](common_params & params, bool value) {
+            params.no_mmproj = !value;
         }
-    ).set_examples(mmproj_examples).set_env("LLAMA_ARG_NO_MMPROJ"));
+    ).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_AUTO"));
     add_opt(common_arg(
+        {"--mmproj-offload"},
         {"--no-mmproj-offload"},
-        "do not offload multimodal projector to GPU",
-        [](common_params & params) {
-            params.mmproj_use_gpu = false;
+        string_format("whether to enable GPU offloading for multimodal projector (default: %s)", params.mmproj_use_gpu ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.mmproj_use_gpu = value;
         }
-    ).set_examples(mmproj_examples).set_env("LLAMA_ARG_NO_MMPROJ_OFFLOAD"));
+    ).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_OFFLOAD"));
     add_opt(common_arg(
         {"--image", "--audio"}, "FILE",
         "path to an image or audio file. use with multimodal models, can be repeated if you have multiple files\n",
@@ -1923,12 +1974,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_env("LLAMA_ARG_MLOCK"));
     add_opt(common_arg(
+        {"--mmap"},
         {"--no-mmap"},
-        "do not memory-map model (slower load but may reduce pageouts if not using mlock)",
-        [](common_params & params) {
-            params.use_mmap = false;
+        string_format("whether to memory-map model (if disabled, slower load but may reduce pageouts if not using mlock) (default: %s)", params.use_mmap ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.use_mmap = value;
         }
-    ).set_env("LLAMA_ARG_NO_MMAP"));
+    ).set_env("LLAMA_ARG_MMAP"));
     add_opt(common_arg(
         {"--numa"}, "TYPE",
         "attempt optimizations that help on some NUMA systems\n"
@@ -2116,10 +2168,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ));
     add_opt(common_arg(
+        {"--op-offload"},
         {"--no-op-offload"},
-        string_format("disable offloading host tensor operations to device (default: %s)", params.no_op_offload ? "true" : "false"),
-        [](common_params & params) {
-            params.no_op_offload = true;
+        string_format("whether to offload host tensor operations to device (default: %s)", params.no_op_offload ? "false" : "true"),
+        [](common_params & params, bool value) {
+            params.no_op_offload = !value;
         }
     ));
     add_opt(common_arg(
@@ -2315,10 +2368,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_IMATRIX}));
     add_opt(common_arg(
+        {"--ppl"},
         {"--no-ppl"},
-        string_format("do not compute perplexity (default: %s)", params.compute_ppl ? "true" : "false"),
-        [](common_params & params) {
-            params.compute_ppl = false;
+        string_format("whether to compute perplexity (default: %s)", params.compute_ppl ? "true" : "false"),
+        [](common_params & params, bool value) {
+            params.compute_ppl = value;
         }
     ).set_examples({LLAMA_EXAMPLE_IMATRIX}));
     add_opt(common_arg(
@@ -2437,12 +2491,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_API_PREFIX"));
     add_opt(common_arg(
+        {"--webui"},
         {"--no-webui"},
-        string_format("Disable the Web UI (default: %s)", params.webui ? "enabled" : "disabled"),
-        [](common_params & params) {
-            params.webui = false;
+        string_format("whether to enable the Web UI (default: %s)", params.webui ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.webui = value;
         }
-    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_WEBUI"));
+    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_WEBUI"));
     add_opt(common_arg(
         {"--embedding", "--embeddings"},
         string_format("restrict to only support embedding use case; use only with dedicated embedding models (default: %s)", params.embedding ? "enabled" : "disabled"),
@@ -2547,18 +2602,12 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_PROPS"));
     add_opt(common_arg(
         {"--slots"},
-        string_format("enable slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
-        [](common_params & params) {
-            params.endpoint_slots = true;
+        {"--no-slots"},
+        string_format("expose slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.endpoint_slots = value;
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_SLOTS"));
-    add_opt(common_arg(
-        {"--no-slots"},
-        "disables slots monitoring endpoint",
-        [](common_params & params) {
-            params.endpoint_slots = false;
-        }
-    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_ENDPOINT_SLOTS"));
     add_opt(common_arg(
         {"--slot-save-path"}, "PATH",
         "path to save slot kv cache (default: disabled)",
@@ -2609,26 +2658,21 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MODELS_MAX"));
     add_opt(common_arg(
+        {"--models-autoload"},
         {"--no-models-autoload"},
-        "disables automatic loading of models (default: enabled)",
-        [](common_params & params) {
-            params.models_autoload = false;
+        string_format("for router server, whether to automatically load models (default: %s)", params.models_autoload ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.models_autoload = value;
         }
-    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_MODELS_AUTOLOAD"));
+    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MODELS_AUTOLOAD"));
     add_opt(common_arg(
         {"--jinja"},
-        string_format("use jinja template for chat (default: %s)", params.use_jinja ? "enabled" : "disabled"),
-        [](common_params & params) {
-            params.use_jinja = true;
+        {"--no-jinja"},
+        string_format("whether to use jinja template engine for chat (default: %s)", params.use_jinja ? "enabled" : "disabled"),
+        [](common_params & params, bool value) {
+            params.use_jinja = value;
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_MTMD}).set_env("LLAMA_ARG_JINJA"));
-    add_opt(common_arg(
-        {"--no-jinja"},
-        string_format("disable jinja template for chat (default: %s)", params.use_jinja ? "disabled" : "enabled"),
-        [](common_params & params) {
-            params.use_jinja = false;
-        }
-    ).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_MTMD}).set_env("LLAMA_ARG_NO_JINJA"));
     add_opt(common_arg(
         {"--reasoning-format"}, "FORMAT",
         "controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of:\n"
@@ -2673,15 +2717,16 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CHAT_TEMPLATE_FILE"));
     add_opt(common_arg(
+        {"--prefill-assistant"},
         {"--no-prefill-assistant"},
         string_format(
             "whether to prefill the assistant's response if the last message is an assistant message (default: prefill enabled)\n"
             "when this flag is set, if the last message is an assistant message then it will be treated as a full message and not prefilled\n"
         ),
-        [](common_params & params) {
-            params.prefill_assistant = false;
+        [](common_params & params, bool value) {
+            params.prefill_assistant = value;
         }
-    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_PREFILL_ASSISTANT"));
+    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_PREFILL_ASSISTANT"));
     add_opt(common_arg(
         {"-sps", "--slot-prompt-similarity"}, "SIMILARITY",
         string_format("how much the prompt of a request must match the prompt of a slot in order to use that slot (default: %.2f, 0.0 = disabled)\n", params.slot_prompt_similarity),

common/arg.h

@@ -16,6 +16,7 @@ struct common_arg {
     std::set<enum llama_example> examples = {LLAMA_EXAMPLE_COMMON};
     std::set<enum llama_example> excludes = {};
     std::vector<const char *> args;
+    std::vector<const char *> args_neg;  // for negated args like --no-xxx
     const char * value_hint   = nullptr; // help text or example for arg value
     const char * value_hint_2 = nullptr; // for second arg value
     const char * env          = nullptr;
@@ -25,6 +26,7 @@ struct common_arg {
     void (*handler_string) (common_params & params, const std::string &) = nullptr;
     void (*handler_str_str)(common_params & params, const std::string &, const std::string &) = nullptr;
     void (*handler_int)    (common_params & params, int) = nullptr;
+    void (*handler_bool)   (common_params & params, bool) = nullptr;
 
     common_arg() = default;
 
@@ -48,6 +50,13 @@ struct common_arg {
         void (*handler)(common_params & params)
     ) : args(args), help(help), handler_void(handler) {}
 
+    common_arg(
+        const std::initializer_list<const char *> & args,
+        const std::initializer_list<const char *> & args_neg,
+        const std::string & help,
+        void (*handler)(common_params & params, bool)
+    ) : args(args), args_neg(args_neg), help(help), handler_bool(handler) {}
+
     // support 2 values for arg
     common_arg(
         const std::initializer_list<const char *> & args,
@@ -80,6 +89,10 @@ struct common_arg {
         }
         return strcmp(args[0], other.args[0]) == 0;
     }
+
+    // get all args and env vars (including negated args/env)
+    std::vector<std::string> get_args() const;
+    std::vector<std::string> get_env() const;
 };
 
 namespace common_arg_utils {

common/preset.cpp

@@ -23,8 +23,14 @@ std::vector<std::string> common_preset::to_args() const {
         if (opt.value_hint == nullptr && opt.value_hint_2 == nullptr) {
             // flag option, no value
             if (common_arg_utils::is_falsey(value)) {
-                // skip the flag
-                args.pop_back();
+                // use negative arg if available
+                if (!opt.args_neg.empty()) {
+                    args.back() = opt.args_neg.back();
+                } else {
+                    // otherwise, skip the flag
+                    // TODO: maybe throw an error instead?
+                    args.pop_back();
+                }
             }
         }
         if (opt.value_hint != nullptr) {
@@ -141,10 +147,10 @@ static std::map<std::string, std::map<std::string, std::string>> parse_ini_from_
 static std::map<std::string, common_arg> get_map_key_opt(common_params_context & ctx_params) {
     std::map<std::string, common_arg> mapping;
     for (const auto & opt : ctx_params.options) {
-        if (opt.env != nullptr) {
-            mapping[opt.env] = opt;
+        for (const auto & env : opt.get_env()) {
+            mapping[env] = opt;
         }
-        for (const auto & arg : opt.args) {
+        for (const auto & arg : opt.get_args()) {
             mapping[rm_leading_dashes(arg)] = opt;
         }
     }

examples/gen-docs/gen-docs.cpp

@@ -14,12 +14,13 @@ static void write_table_header(std::ofstream & file) {
 static void write_table_entry(std::ofstream & file, const common_arg & opt) {
     file << "| `";
     // args
-    for (const auto & arg : opt.args) {
-    if (arg == opt.args.front()) {
+    auto all_args = opt.get_args();
+    for (const auto & arg : all_args) {
+    if (arg == all_args.front()) {
             file << arg;
-            if (opt.args.size() > 1) file << ", ";
+            if (all_args.size() > 1) file << ", ";
         } else {
-            file << arg << (arg != opt.args.back() ? ", " : "");
+            file << arg << (arg != all_args.back() ? ", " : "");
         }
     }
     // value hint

examples/model-conversion/scripts/causal/compare-logits.py

@@ -1,10 +1,13 @@
 #!/usr/bin/env python3
 
-import numpy as np
 import sys
-import os
+import numpy as np
 from pathlib import Path
 
+# Add utils directory to path for direct script execution
+sys.path.insert(0, str(Path(__file__).parent.parent / "utils"))
+from common import get_model_name_from_env_path  # type: ignore[import-not-found]
+
 def quick_logits_check(pytorch_file, llamacpp_file):
     """Lightweight sanity check before NMSE"""
 
@@ -35,20 +38,13 @@ def quick_logits_check(pytorch_file, llamacpp_file):
     return True
 
 def main():
-    model_path = os.getenv('MODEL_PATH')
-    if not model_path:
-        print("Error: MODEL_PATH environment variable not set")
-        sys.exit(1)
-
-    if not os.path.exists(model_path):
-        print(f"Error: Model file not found: {model_path}")
-        sys.exit(1)
-
-    model_name = os.path.basename(model_path)
+    model_name = get_model_name_from_env_path('MODEL_PATH')
     data_dir = Path("data")
-
     pytorch_file = data_dir / f"pytorch-{model_name}.bin"
-    llamacpp_file = data_dir / f"llamacpp-{model_name}.bin"
+
+    llamacpp_model_name = get_model_name_from_env_path('CONVERTED_MODEL')
+    print(f"Using converted model: {llamacpp_model_name}")
+    llamacpp_file = data_dir / f"llamacpp-{llamacpp_model_name}.bin"
 
     if not pytorch_file.exists():
         print(f"Error: PyTorch logits file not found: {pytorch_file}")

examples/model-conversion/scripts/utils/check-nmse.py

@@ -5,6 +5,7 @@ import sys
 import os
 import argparse
 from pathlib import Path
+from common import get_model_name_from_env_path  # type: ignore[import-not-found]
 
 def calculate_nmse(reference, test):
     mse = np.mean((test - reference) ** 2)
@@ -67,11 +68,13 @@ def main():
     parser.add_argument('-m', '--model-path', required=True,  help='Path to the model directory')
     args = parser.parse_args()
 
-    model_name = os.path.basename(args.model_path)
+    model_name = get_model_name_from_env_path('MODEL_PATH')
     data_dir = Path("data")
 
     pytorch_file = data_dir / f"pytorch-{model_name}.bin"
-    llamacpp_file = data_dir / f"llamacpp-{model_name}.bin"
+
+    llamacpp_model_name = get_model_name_from_env_path('CONVERTED_MODEL')
+    llamacpp_file = data_dir / f"llamacpp-{llamacpp_model_name}.bin"
 
     print(f"Model name: {model_name}")
     print(f"PyTorch logits file: {pytorch_file}")

examples/model-conversion/scripts/utils/common.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python3
+
+import os
+import sys
+
+def get_model_name_from_env_path(env_path_name):
+    model_path = os.getenv(env_path_name)
+    if not model_path:
+        print(f"Error: {env_path_name} environment variable not set")
+        sys.exit(1)
+
+    if not os.path.exists(model_path):
+        print(f"Error: Model file not found: {model_path}")
+        sys.exit(1)
+
+    name = os.path.basename(os.path.normpath(model_path))
+    if name.endswith(".gguf"):
+        name = name[:-5]
+
+    return name

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -757,7 +757,8 @@ struct vk_device_struct {
 
     vk_pipeline pipeline_flash_attn_split_k_reduce;
 
-    vk_pipeline pipeline_topk_moe[num_topk_moe_pipelines][TOPK_MOE_COUNT];
+    // [2] is for whether to take n_experts from spec constant (0) or push constant (1)
+    vk_pipeline pipeline_topk_moe[num_topk_moe_pipelines][TOPK_MOE_COUNT][2];
 
     std::vector<vk_pipeline_ref> all_pipelines;
 
@@ -1149,6 +1150,7 @@ static_assert(sizeof(vk_op_multi_add_push_constants) <= 256);
 
 struct vk_op_topk_moe_push_constants {
     uint32_t n_rows;
+    uint32_t n_experts_push;
     uint32_t n_expert_used;
     float clamp_min;
     float clamp_max;
@@ -4204,10 +4206,12 @@ static void ggml_vk_load_shaders(vk_device& device) {
     ggml_vk_create_pipeline(device, device->pipeline_conv2d_dw_whcn_f16_f32, "conv2d_dw_whcn_f16_f32", conv2d_dw_whcn_f16_f32_len, conv2d_dw_whcn_f16_f32_data, "main", 3, sizeof(vk_op_conv2d_dw_push_constants), {512, 1, 1}, {}, 1);
     ggml_vk_create_pipeline(device, device->pipeline_conv2d_dw_cwhn_f16_f32, "conv2d_dw_cwhn_f16_f32", conv2d_dw_cwhn_f16_f32_len, conv2d_dw_cwhn_f16_f32_data, "main", 3, sizeof(vk_op_conv2d_dw_push_constants), {512, 1, 1}, {}, 1);
 
-    for (uint32_t i = 0; i < num_topk_moe_pipelines; ++i) {
-        ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_EARLY_SOFTMAX],      "topk_moe_f32_early_softmax_"+std::to_string(i),       topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 0, 0}, 1, true, true, device->subgroup_size);
-        ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_EARLY_SOFTMAX_NORM], "topk_moe_f32_early_softmax_norm"+std::to_string(i),   topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 1, 0}, 1, true, true, device->subgroup_size);
-        ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_LATE_SOFTMAX],       "topk_moe_f32_late_softmax"+std::to_string(i),         topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 0, 1}, 1, true, true, device->subgroup_size);
+    for (uint32_t use_push = 0; use_push < 2; ++use_push) {
+        for (uint32_t i = 0; i < num_topk_moe_pipelines; ++i) {
+            ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_EARLY_SOFTMAX][use_push],      "topk_moe_f32_early_softmax_"+std::to_string(i),       topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 0, 0, use_push}, 1, true, true, device->subgroup_size);
+            ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_EARLY_SOFTMAX_NORM][use_push], "topk_moe_f32_early_softmax_norm"+std::to_string(i),   topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 1, 0, use_push}, 1, true, true, device->subgroup_size);
+            ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_LATE_SOFTMAX][use_push],       "topk_moe_f32_late_softmax"+std::to_string(i),         topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 0, 1, use_push}, 1, true, true, device->subgroup_size);
+        }
     }
 
     for (auto &c : compiles) {
@@ -8554,7 +8558,9 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
             uint32_t idx = (uint32_t)ceilf(log2f(float(dst->ne[0])));
             GGML_ASSERT(idx < num_topk_moe_pipelines);
             topk_moe_mode mode = ggml_vk_num_additional_ops_to_topk_moe_mode(ctx->num_additional_fused_ops);
-            return ctx->device->pipeline_topk_moe[idx][mode];
+            // use n_experts from push constant if it's not equal to the power of two spec constant
+            bool use_push = dst->ne[0] != (1u << idx);
+            return ctx->device->pipeline_topk_moe[idx][mode][use_push];
         }
 
         if (src0->type == GGML_TYPE_F32 && (src1 == nullptr || src1->type == GGML_TYPE_F32) && dst->type == GGML_TYPE_F32) {
@@ -10158,6 +10164,7 @@ static void ggml_vk_topk_moe(ggml_backend_vk_context * ctx, vk_context& subctx,
 
     vk_op_topk_moe_push_constants pc {};
     pc.n_rows = n_rows;
+    pc.n_experts_push = n_experts;
     pc.n_expert_used = n_expert_used;
     if (mode == TOPK_MOE_EARLY_SOFTMAX_NORM) {
         ggml_tensor * clamp = cgraph->nodes[node_idx + 7];
@@ -12832,8 +12839,7 @@ static bool ggml_vk_can_fuse_topk_moe(ggml_backend_vk_context * ctx, const struc
     }
 
     const int n_expert = softmax->ne[0];
-    // n_expert must be a power of 2
-    if (!is_pow2(n_expert) || n_expert > (1 << (num_topk_moe_pipelines-1))) {
+    if (n_expert > (1 << (num_topk_moe_pipelines-1))) {
         return false;
     }
 

ggml/src/ggml-vulkan/vulkan-shaders/topk_moe.comp

@@ -10,6 +10,7 @@
 layout (push_constant) uniform parameter
 {
     uint n_rows;
+    uint n_experts_push;
     uint n_expert_used;
     float clamp_min;
     float clamp_max;
@@ -18,11 +19,16 @@ layout (push_constant) uniform parameter
 layout(local_size_x_id = 0, local_size_y = 4, local_size_z = 1) in;
 
 layout(constant_id = 0) const uint WARP_SIZE = 32;
-layout(constant_id = 1) const uint n_experts = 512;
+layout(constant_id = 1) const uint n_experts_spec = 512;
 layout(constant_id = 2) const bool with_norm = true;
 layout(constant_id = 3) const bool late_softmax = false;
+layout(constant_id = 4) const bool nexperts_use_push = false;
 
-const uint experts_per_thread = (n_experts > WARP_SIZE) ? n_experts / WARP_SIZE : 1;
+uint n_experts = nexperts_use_push ? n_experts_push : n_experts_spec;
+
+#define CEIL_DIV(a, b) (((a) + (b) - 1) / (b))
+
+const uint experts_per_thread = CEIL_DIV(n_experts_spec, WARP_SIZE);
 
 layout (binding = 0, std430) readonly buffer Logits {float logits[];};
 layout (binding = 1, std430) writeonly buffer Weights {float weights[];};
@@ -94,7 +100,7 @@ void main() {
     }
 
     if (!late_softmax) {
-        softmax_warp_inplace(wt, n_experts, lane, false);
+        softmax_warp_inplace(wt, n_experts, lane, nexperts_use_push);
     }
 
     // at this point, each thread holds a portion of softmax,

pyrightconfig.json

@@ -1,5 +1,5 @@
 {
-  "extraPaths": ["gguf-py"],
+  "extraPaths": ["gguf-py", "examples/model-conversion/scripts"],
   "pythonVersion": "3.9",
   "pythonPlatform": "All",
   "reportUnusedImport": "warning",

tests/test-arg-parser.cpp

@@ -20,20 +20,20 @@ int main(void) {
             std::unordered_set<std::string> seen_env_vars;
             for (const auto & opt : ctx_arg.options) {
                 // check for args duplications
-                for (const auto & arg : opt.args) {
+                for (const auto & arg : opt.get_args()) {
                     if (seen_args.find(arg) == seen_args.end()) {
                         seen_args.insert(arg);
                     } else {
-                        fprintf(stderr, "test-arg-parser: found different handlers for the same argument: %s", arg);
+                        fprintf(stderr, "test-arg-parser: found different handlers for the same argument: %s", arg.c_str());
                         exit(1);
                     }
                 }
                 // check for env var duplications
-                if (opt.env) {
-                    if (seen_env_vars.find(opt.env) == seen_env_vars.end()) {
-                        seen_env_vars.insert(opt.env);
+                for (const auto & env : opt.get_env()) {
+                    if (seen_env_vars.find(env) == seen_env_vars.end()) {
+                        seen_env_vars.insert(env);
                     } else {
-                        fprintf(stderr, "test-arg-parser: found different handlers for the same env var: %s", opt.env);
+                        fprintf(stderr, "test-arg-parser: found different handlers for the same env var: %s", env.c_str());
                         exit(1);
                     }
                 }
@@ -115,6 +115,14 @@ int main(void) {
     assert(params.model.path == "blah.gguf");
     assert(params.cpuparams.n_threads == 1010);
 
+    printf("test-arg-parser: test negated environment variables\n\n");
+
+    setenv("LLAMA_ARG_MMAP", "0", true);
+    setenv("LLAMA_ARG_NO_PERF", "1", true); // legacy format
+    argv = {"binary_name"};
+    assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
+    assert(params.use_mmap == false);
+    assert(params.no_perf == true);
 
     printf("test-arg-parser: test environment variables being overwritten\n\n");
 

tests/test-backend-ops.cpp

@@ -7971,8 +7971,12 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
 
     for (bool with_norm : {false, true}) {
         test_cases.emplace_back(new test_topk_moe({8, 22, 1, 1}, 4, with_norm));
+        test_cases.emplace_back(new test_topk_moe({31, 22, 1, 1}, 8, with_norm));
         test_cases.emplace_back(new test_topk_moe({32, 22, 1, 1}, 8, with_norm));
+        test_cases.emplace_back(new test_topk_moe({40, 22, 1, 1}, 8, with_norm));
+        test_cases.emplace_back(new test_topk_moe({71, 22, 1, 1}, 8, with_norm));
         test_cases.emplace_back(new test_topk_moe({128, 1, 1, 1}, 128, with_norm));
+        test_cases.emplace_back(new test_topk_moe({129, 1, 1, 1}, 128, with_norm));
     }
 
     test_cases.emplace_back(new test_topk_moe({ 8, 22, 1, 1 }, 4, /*with_norm*/ false, /*delayed_softmax*/ true));

tools/server/README.md

@@ -54,9 +54,8 @@ For the ful list of features, please refer to [server's changelog](https://githu
 | `--swa-full` | use full-size SWA cache (default: false)<br/>[(more info)](https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)<br/>(env: LLAMA_ARG_SWA_FULL) |
 | `--kv-unified, -kvu` | use single unified KV buffer for the KV cache of all sequences (default: false)<br/>[(more info)](https://github.com/ggml-org/llama.cpp/pull/14363)<br/>(env: LLAMA_ARG_KV_UNIFIED) |
 | `-fa, --flash-attn [on\|off\|auto]` | set Flash Attention use ('on', 'off', or 'auto', default: 'auto')<br/>(env: LLAMA_ARG_FLASH_ATTN) |
-| `--no-perf` | disable internal libllama performance timings (default: false)<br/>(env: LLAMA_ARG_NO_PERF) |
-| `-e, --escape` | process escapes sequences (\n, \r, \t, \', \", \\) (default: true) |
-| `--no-escape` | do not process escape sequences |
+| `--perf, --no-perf` | whether to enable internal libllama performance timings (default: false)<br/>(env: LLAMA_ARG_PERF) |
+| `-e, --escape, --no-escape` | whether to process escapes sequences (\n, \r, \t, \', \", \\) (default: true) |
 | `--rope-scaling {none,linear,yarn}` | RoPE frequency scaling method, defaults to linear unless specified by the model<br/>(env: LLAMA_ARG_ROPE_SCALING_TYPE) |
 | `--rope-scale N` | RoPE context scaling factor, expands context by a factor of N<br/>(env: LLAMA_ARG_ROPE_SCALE) |
 | `--rope-freq-base N` | RoPE base frequency, used by NTK-aware scaling (default: loaded from model)<br/>(env: LLAMA_ARG_ROPE_FREQ_BASE) |
@@ -66,15 +65,15 @@ For the ful list of features, please refer to [server's changelog](https://githu
 | `--yarn-attn-factor N` | YaRN: scale sqrt(t) or attention magnitude (default: -1.0)<br/>(env: LLAMA_ARG_YARN_ATTN_FACTOR) |
 | `--yarn-beta-slow N` | YaRN: high correction dim or alpha (default: -1.0)<br/>(env: LLAMA_ARG_YARN_BETA_SLOW) |
 | `--yarn-beta-fast N` | YaRN: low correction dim or beta (default: -1.0)<br/>(env: LLAMA_ARG_YARN_BETA_FAST) |
-| `-nkvo, --no-kv-offload` | disable KV offload<br/>(env: LLAMA_ARG_NO_KV_OFFLOAD) |
-| `-nr, --no-repack` | disable weight repacking<br/>(env: LLAMA_ARG_NO_REPACK) |
-| `--no-host` | bypass host buffer allowing extra buffers to be used<br/>(env: LLAMA_ARG_NO_HOST) |
+| `-kvo, --kv-offload, -nkvo, --no-kv-offload` | whether to enable KV cache offloading (default: enabled)<br/>(env: LLAMA_ARG_KV_OFFLOAD) |
+| `--repack, -nr, --no-repack` | whether to enable weight repacking (default: enabled)<br/>(env: LLAMA_ARG_REPACK) |
+| `--no-host` | bypass host buffer allowing extra buffers to be used<br/>(env: LLAMA_ARG_HOST) |
 | `-ctk, --cache-type-k TYPE` | KV cache data type for K<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_K) |
 | `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
 | `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
 | `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
 | `--mlock` | force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
-| `--no-mmap` | do not memory-map model (slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_NO_MMAP) |
+| `--mmap, --no-mmap` | whether to memory-map model (if disabled, slower load but may reduce pageouts if not using mlock) (default: enabled)<br/>(env: LLAMA_ARG_MMAP) |
 | `--numa TYPE` | attempt optimizations that help on some NUMA systems<br/>- distribute: spread execution evenly over all nodes<br/>- isolate: only spawn threads on CPUs on the node that execution started on<br/>- numactl: use the CPU map provided by numactl<br/>if run without this previously, it is recommended to drop the system page cache before using this<br/>see https://github.com/ggml-org/llama.cpp/issues/1437<br/>(env: LLAMA_ARG_NUMA) |
 | `-dev, --device <dev1,dev2,..>` | comma-separated list of devices to use for offloading (none = don't offload)<br/>use --list-devices to see a list of available devices<br/>(env: LLAMA_ARG_DEVICE) |
 | `--list-devices` | print list of available devices and exit |
@@ -87,7 +86,7 @@ For the ful list of features, please refer to [server's changelog](https://githu
 | `-mg, --main-gpu INDEX` | the GPU to use for the model (with split-mode = none), or for intermediate results and KV (with split-mode = row) (default: 0)<br/>(env: LLAMA_ARG_MAIN_GPU) |
 | `--check-tensors` | check model tensor data for invalid values (default: false) |
 | `--override-kv KEY=TYPE:VALUE` | advanced option to override model metadata by key. may be specified multiple times.<br/>types: int, float, bool, str. example: --override-kv tokenizer.ggml.add_bos_token=bool:false |
-| `--no-op-offload` | disable offloading host tensor operations to device (default: false) |
+| `--op-offload, --no-op-offload` | whether to offload host tensor operations to device (default: true) |
 | `--lora FNAME` | path to LoRA adapter (can be repeated to use multiple adapters) |
 | `--lora-scaled FNAME SCALE` | path to LoRA adapter with user defined scaling (can be repeated to use multiple adapters) |
 | `--control-vector FNAME` | add a control vector<br/>note: this argument can be repeated to add multiple control vectors |
@@ -157,19 +156,18 @@ For the ful list of features, please refer to [server's changelog](https://githu
 | -------- | ----------- |
 | `--ctx-checkpoints, --swa-checkpoints N` | max number of context checkpoints to create per slot (default: 8)<br/>[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)<br/>(env: LLAMA_ARG_CTX_CHECKPOINTS) |
 | `--cache-ram, -cram N` | set the maximum cache size in MiB (default: 8192, -1 - no limit, 0 - disable)<br/>[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)<br/>(env: LLAMA_ARG_CACHE_RAM) |
-| `--no-context-shift` | disables context shift on infinite text generation (default: enabled)<br/>(env: LLAMA_ARG_NO_CONTEXT_SHIFT) |
-| `--context-shift` | enables context shift on infinite text generation (default: disabled)<br/>(env: LLAMA_ARG_CONTEXT_SHIFT) |
+| `--context-shift, --no-context-shift` | whether to use context shift on infinite text generation (default: disabled)<br/>(env: LLAMA_ARG_CONTEXT_SHIFT) |
 | `-r, --reverse-prompt PROMPT` | halt generation at PROMPT, return control in interactive mode<br/> |
 | `-sp, --special` | special tokens output enabled (default: false) |
-| `--no-warmup` | skip warming up the model with an empty run |
+| `--warmup, --no-warmup` | whether to perform warmup with an empty run (default: enabled) |
 | `--spm-infill` | use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this. (default: disabled) |
 | `--pooling {none,mean,cls,last,rank}` | pooling type for embeddings, use model default if unspecified<br/>(env: LLAMA_ARG_POOLING) |
-| `-cb, --cont-batching` | enable continuous batching (a.k.a dynamic batching) (default: enabled)<br/>(env: LLAMA_ARG_CONT_BATCHING) |
-| `-nocb, --no-cont-batching` | disable continuous batching<br/>(env: LLAMA_ARG_NO_CONT_BATCHING) |
+| `-cb, --cont-batching, -nocb, --no-cont-batching` | whether to enable continuous batching (a.k.a dynamic batching) (default: enabled)<br/>(env: LLAMA_ARG_CONT_BATCHING) |
+| `-cb, --cont-batching, -nocb, --no-cont-batching` | whether to enable continuous batching (a.k.a dynamic batching) (default: enabled)<br/>(env: LLAMA_ARG_CONT_BATCHING) |
 | `-mm, --mmproj FILE` | path to a multimodal projector file. see tools/mtmd/README.md<br/>note: if -hf is used, this argument can be omitted<br/>(env: LLAMA_ARG_MMPROJ) |
 | `-mmu, --mmproj-url URL` | URL to a multimodal projector file. see tools/mtmd/README.md<br/>(env: LLAMA_ARG_MMPROJ_URL) |
-| `--no-mmproj` | explicitly disable multimodal projector, useful when using -hf<br/>(env: LLAMA_ARG_NO_MMPROJ) |
-| `--no-mmproj-offload` | do not offload multimodal projector to GPU<br/>(env: LLAMA_ARG_NO_MMPROJ_OFFLOAD) |
+| `--mmproj-auto, --no-mmproj, --no-mmproj-auto` | whether to use multimodal projector file (if available), useful when using -hf (default: enabled)<br/>(env: LLAMA_ARG_MMPROJ_AUTO) |
+| `--mmproj-offload, --no-mmproj-offload` | whether to enable GPU offloading for multimodal projector (default: enabled)<br/>(env: LLAMA_ARG_MMPROJ_OFFLOAD) |
 | `--image-min-tokens N` | minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MIN_TOKENS) |
 | `--image-max-tokens N` | maximum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MAX_TOKENS) |
 | `--override-tensor-draft, -otd <tensor name pattern>=<buffer type>,...` | override tensor buffer type for draft model |
@@ -180,7 +178,7 @@ For the ful list of features, please refer to [server's changelog](https://githu
 | `--port PORT` | port to listen (default: 8080)<br/>(env: LLAMA_ARG_PORT) |
 | `--path PATH` | path to serve static files from (default: )<br/>(env: LLAMA_ARG_STATIC_PATH) |
 | `--api-prefix PREFIX` | prefix path the server serves from, without the trailing slash (default: )<br/>(env: LLAMA_ARG_API_PREFIX) |
-| `--no-webui` | Disable the Web UI (default: enabled)<br/>(env: LLAMA_ARG_NO_WEBUI) |
+| `--webui, --no-webui` | whether to enable the Web UI (default: enabled)<br/>(env: LLAMA_ARG_WEBUI) |
 | `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)<br/>(env: LLAMA_ARG_EMBEDDINGS) |
 | `--reranking, --rerank` | enable reranking endpoint on server (default: disabled)<br/>(env: LLAMA_ARG_RERANKING) |
 | `--api-key KEY` | API key to use for authentication (default: none)<br/>(env: LLAMA_API_KEY) |
@@ -193,20 +191,19 @@ For the ful list of features, please refer to [server's changelog](https://githu
 | `--cache-reuse N` | min chunk size to attempt reusing from the cache via KV shifting (default: 0)<br/>[(card)](https://ggml.ai/f0.png)<br/>(env: LLAMA_ARG_CACHE_REUSE) |
 | `--metrics` | enable prometheus compatible metrics endpoint (default: disabled)<br/>(env: LLAMA_ARG_ENDPOINT_METRICS) |
 | `--props` | enable changing global properties via POST /props (default: disabled)<br/>(env: LLAMA_ARG_ENDPOINT_PROPS) |
-| `--slots` | enable slots monitoring endpoint (default: enabled)<br/>(env: LLAMA_ARG_ENDPOINT_SLOTS) |
-| `--no-slots` | disables slots monitoring endpoint<br/>(env: LLAMA_ARG_NO_ENDPOINT_SLOTS) |
+| `--slots, --no-slots` | expose slots monitoring endpoint (default: enabled)<br/>(env: LLAMA_ARG_ENDPOINT_SLOTS) |
 | `--slot-save-path PATH` | path to save slot kv cache (default: disabled) |
+| `--media-path PATH` | directory for loading local media files; files can be accessed via file:// URLs using relative paths (default: disabled) |
 | `--models-dir PATH` | directory containing models for the router server (default: disabled)<br/>(env: LLAMA_ARG_MODELS_DIR) |
+| `--models-preset PATH` | path to INI file containing model presets for the router server (default: disabled)<br/>(env: LLAMA_ARG_MODELS_PRESET) |
 | `--models-max N` | for router server, maximum number of models to load simultaneously (default: 4, 0 = unlimited)<br/>(env: LLAMA_ARG_MODELS_MAX) |
-| `--models-allow-extra-args` | for router server, allow extra arguments for models; important: some arguments can allow users to access local file system, use with caution (default: disabled)<br/>(env: LLAMA_ARG_MODELS_ALLOW_EXTRA_ARGS) |
-| `--no-models-autoload` | disables automatic loading of models (default: enabled)<br/>(env: LLAMA_ARG_NO_MODELS_AUTOLOAD) |
-| `--jinja` | use jinja template for chat (default: enabled)<br/><br/>(env: LLAMA_ARG_JINJA) |
-| `--no-jinja` | disable jinja template for chat (default: enabled)<br/><br/>(env: LLAMA_ARG_NO_JINJA) |
+| `--models-autoload, --no-models-autoload` | for router server, whether to automatically load models (default: enabled)<br/>(env: LLAMA_ARG_MODELS_AUTOLOAD) |
+| `--jinja, --no-jinja` | whether to use jinja template engine for chat (default: enabled)<br/>(env: LLAMA_ARG_JINJA) |
 | `--reasoning-format FORMAT` | controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of:<br/>- none: leaves thoughts unparsed in `message.content`<br/>- deepseek: puts thoughts in `message.reasoning_content`<br/>- deepseek-legacy: keeps `<think>` tags in `message.content` while also populating `message.reasoning_content`<br/>(default: auto)<br/>(env: LLAMA_ARG_THINK) |
 | `--reasoning-budget N` | controls the amount of thinking allowed; currently only one of: -1 for unrestricted thinking budget, or 0 to disable thinking (default: -1)<br/>(env: LLAMA_ARG_THINK_BUDGET) |
 | `--chat-template JINJA_TEMPLATE` | set custom jinja chat template (default: template taken from model's metadata)<br/>if suffix/prefix are specified, template will be disabled<br/>only commonly used templates are accepted (unless --jinja is set before this flag):<br/>list of built-in templates:<br/>bailing, bailing-think, bailing2, chatglm3, chatglm4, chatml, command-r, deepseek, deepseek2, deepseek3, exaone3, exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, grok-2, hunyuan-dense, hunyuan-moe, kimi-k2, llama2, llama2-sys, llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm, mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7, mistral-v7-tekken, monarch, openchat, orion, pangu-embedded, phi3, phi4, rwkv-world, seed_oss, smolvlm, vicuna, vicuna-orca, yandex, zephyr<br/>(env: LLAMA_ARG_CHAT_TEMPLATE) |
 | `--chat-template-file JINJA_TEMPLATE_FILE` | set custom jinja chat template file (default: template taken from model's metadata)<br/>if suffix/prefix are specified, template will be disabled<br/>only commonly used templates are accepted (unless --jinja is set before this flag):<br/>list of built-in templates:<br/>bailing, bailing-think, bailing2, chatglm3, chatglm4, chatml, command-r, deepseek, deepseek2, deepseek3, exaone3, exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, grok-2, hunyuan-dense, hunyuan-moe, kimi-k2, llama2, llama2-sys, llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm, mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7, mistral-v7-tekken, monarch, openchat, orion, pangu-embedded, phi3, phi4, rwkv-world, seed_oss, smolvlm, vicuna, vicuna-orca, yandex, zephyr<br/>(env: LLAMA_ARG_CHAT_TEMPLATE_FILE) |
-| `--no-prefill-assistant` | whether to prefill the assistant's response if the last message is an assistant message (default: prefill enabled)<br/>when this flag is set, if the last message is an assistant message then it will be treated as a full message and not prefilled<br/><br/>(env: LLAMA_ARG_NO_PREFILL_ASSISTANT) |
+| `--prefill-assistant, --no-prefill-assistant` | whether to prefill the assistant's response if the last message is an assistant message (default: prefill enabled)<br/>when this flag is set, if the last message is an assistant message then it will be treated as a full message and not prefilled<br/><br/>(env: LLAMA_ARG_PREFILL_ASSISTANT) |
 | `-sps, --slot-prompt-similarity SIMILARITY` | how much the prompt of a request must match the prompt of a slot in order to use that slot (default: 0.10, 0.0 = disabled)<br/> |
 | `--lora-init-without-apply` | load LoRA adapters without applying them (apply later via POST /lora-adapters) (default: disabled) |
 | `-td, --threads-draft N` | number of threads to use during generation (default: same as --threads) |
@@ -236,6 +233,11 @@ For the ful list of features, please refer to [server's changelog](https://githu
 
 Note: If both command line argument and environment variable are both set for the same param, the argument will take precedence over env var.
 
+For boolean options like `--mmap` or `--kv-offload`, the environment variable is handled as shown in this example:
+- `LLAMA_ARG_MMAP=true` means enabled, other accepted values are: `1`, `on`, `enabled`
+- `LLAMA_ARG_MMAP=false` means disabled, other accepted values are: `0`, `off`, `disabled`
+- If `LLAMA_ARG_NO_MMAP` is present (no matter the value), it means disabling mmap
+
 Example usage of docker compose with environment variables:
 
 ```yml