Merge branch 'master' into llamacli-tools

Author: bandoti

.github/workflows/close-issue.yml

@@ -17,7 +17,7 @@ jobs:
     steps:
       - uses: actions/stale@v5
         with:
-          exempt-issue-labels: "refactor,help wanted,good first issue,research,bug"
+          exempt-issue-labels: "refactor,help wanted,good first issue,research,bug,roadmap"
           days-before-issue-stale: 30
           days-before-issue-close: 14
           stale-issue-label: "stale"

AUTHORS

@@ -136,6 +136,7 @@ Instructions for adding support for new models: [HOWTO-add-model.md](docs/develo
 - Rust (more features): [edgenai/llama_cpp-rs](https://github.com/edgenai/llama_cpp-rs)
 - Rust (nicer API): [mdrokz/rust-llama.cpp](https://github.com/mdrokz/rust-llama.cpp)
 - Rust (more direct bindings): [utilityai/llama-cpp-rs](https://github.com/utilityai/llama-cpp-rs)
+- Rust (automated build from crates.io): [ShelbyJenkins/llm_client](https://github.com/ShelbyJenkins/llm_client)
 - C#/.NET: [SciSharp/LLamaSharp](https://github.com/SciSharp/LLamaSharp)
 - C#/VB.NET (more features - community license): [LM-Kit.NET](https://docs.lm-kit.com/lm-kit-net/index.html)
 - Scala 3: [donderom/llm4s](https://github.com/donderom/llm4s)

README.md

@@ -1465,15 +1465,28 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         {"--list-devices"},
         "print list of available devices and exit",
         [](common_params &) {
-            printf("Available devices:\n");
+            std::vector<ggml_backend_dev_t> rpc_devices;
+            std::vector<ggml_backend_dev_t> all_devices;
             for (size_t i = 0; i < ggml_backend_dev_count(); ++i) {
                 auto * dev = ggml_backend_dev_get(i);
                 if (ggml_backend_dev_type(dev) == GGML_BACKEND_DEVICE_TYPE_GPU) {
-                    size_t free, total;
-                    ggml_backend_dev_memory(dev, &free, &total);
-                    printf("  %s: %s (%zu MiB, %zu MiB free)\n", ggml_backend_dev_name(dev), ggml_backend_dev_description(dev), total / 1024 / 1024, free / 1024 / 1024);
+                    ggml_backend_reg_t reg = ggml_backend_dev_backend_reg(dev);
+                    if (ggml_backend_reg_name(reg) == std::string("RPC")) {
+                        rpc_devices.push_back(dev);
+                    } else {
+                        all_devices.push_back(dev);
+                    }
                 }
             }
+            // insert RPC devices in front
+            all_devices.insert(all_devices.begin(), rpc_devices.begin(), rpc_devices.end());
+            printf("Available devices:\n");
+            for (size_t i = 0; i < all_devices.size(); ++i) {
+                auto * dev = all_devices[i];
+                size_t free, total;
+                ggml_backend_dev_memory(dev, &free, &total);
+                printf("  %s: %s (%zu MiB, %zu MiB free)\n", ggml_backend_dev_name(dev), ggml_backend_dev_description(dev), total / 1024 / 1024, free / 1024 / 1024);
+            }
             exit(0);
         }
     ));

common/arg.cpp

@@ -365,7 +365,7 @@ static common_chat_params common_chat_params_init_command_r7b(const common_chat_
     return data;
 }
 static common_chat_msg common_chat_parse_command_r7b(const std::string & input) {
-    static std::regex response_regex("<\\|START_RESPONSE\\|>(.*?)<\\|END_RESPONSE\\|>");
+    static std::regex response_regex("<\\|START_RESPONSE\\|>([\\s\\S\\n\\r]*?)<\\|END_RESPONSE\\|>");
     static std::regex thought_action_regex("<\\|START_THINKING\\|>([\\s\\S\\n\\r]*?)<\\|END_THINKING\\|><\\|START_ACTION\\|>([\\s\\S\\n\\r]*?)<\\|END_ACTION\\|>");
     std::smatch match;
 

common/chat.cpp

@@ -1932,11 +1932,19 @@ std::string common_chat_format_example(const common_chat_templates & tmpl, bool
     return common_chat_apply_template(tmpl, msgs, true, use_jinja);
 }
 
+#define CHATML_TEMPLATE_SRC \
+    "{%- for message in messages -%}\n" \
+    "  {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' -}}\n" \
+    "{%- endfor -%}\n" \
+    "{%- if add_generation_prompt -%}\n" \
+    "  {{- '<|im_start|>assistant\n' -}}\n" \
+    "{%- endif -%}"
+
 common_chat_templates common_chat_templates_from_model(const struct llama_model * model, const std::string & chat_template_override)
 {
-    auto vocab = llama_model_get_vocab(model);
-    std::string default_template_src = chat_template_override;
-    std::string template_tool_use_src = chat_template_override;
+    std::string default_template_src;
+    std::string template_tool_use_src;
+
     bool has_explicit_template = !chat_template_override.empty();
     if (chat_template_override.empty()) {
         auto str = llama_model_chat_template(model, /* name */ nullptr);
@@ -1949,21 +1957,21 @@ common_chat_templates common_chat_templates_from_model(const struct llama_model
             template_tool_use_src = str;
             has_explicit_template = true;
         }
+    } else {
+        default_template_src = chat_template_override;
     }
     if (default_template_src.empty() || default_template_src == "chatml") {
         if (!template_tool_use_src.empty()) {
             default_template_src = template_tool_use_src;
         } else {
-            default_template_src = R"(
-                {%- for message in messages -%}
-                    {{- "<|im_start|>" + message.role + "\n" + message.content + "<|im_end|>\n" -}}
-                {%- endfor -%}
-                {%- if add_generation_prompt -%}
-                    {{- "<|im_start|>assistant\n" -}}
-                {%- endif -%}
-            )";
+            default_template_src = CHATML_TEMPLATE_SRC;
         }
     }
+    std::string token_bos;
+    std::string token_eos;
+    // TODO: update logic that adds BOS and EOS tokens to the tokenized prompt, in favour of the template.
+#if 0
+    auto vocab = llama_model_get_vocab(model);
     const auto get_token = [&](llama_token token, const char * name, const char * jinja_variable_name) {
         if (token == LLAMA_TOKEN_NULL) {
             if (default_template_src.find(jinja_variable_name) != std::string::npos
@@ -1975,15 +1983,25 @@ common_chat_templates common_chat_templates_from_model(const struct llama_model
             return common_token_to_piece(vocab, token, true);
         }
     };
-    auto token_bos = get_token(llama_vocab_bos(vocab), "BOS", "bos_token");
-    auto token_eos = get_token(llama_vocab_eos(vocab), "EOS", "eos_token");
-    return {
-        has_explicit_template,
-        std::make_unique<minja::chat_template>(default_template_src, token_bos, token_eos),
-        template_tool_use_src.empty()
-            ? nullptr
-            : std::make_unique<minja::chat_template>(template_tool_use_src, token_bos, token_eos)
-    };
+    token_bos = get_token(llama_vocab_bos(vocab), "BOS", "bos_token");
+    token_eos = get_token(llama_vocab_eos(vocab), "EOS", "eos_token");
+#endif
+    try {
+        return {
+            has_explicit_template,
+            std::make_unique<minja::chat_template>(default_template_src, token_bos, token_eos),
+            template_tool_use_src.empty()
+                ? nullptr
+                : std::make_unique<minja::chat_template>(template_tool_use_src, token_bos, token_eos),
+        };
+    } catch (const std::exception & e) {
+        LOG_ERR("%s: failed to parse chat template: %s\n", __func__, e.what());
+        return {
+            has_explicit_template,
+            std::make_unique<minja::chat_template>(CHATML_TEMPLATE_SRC, token_bos, token_eos),
+            nullptr,
+        };
+    }
 }
 
 //

common/common.cpp

@@ -31,6 +31,11 @@ defer {
     llama_model_free(model)
 }
 
+guard let vocab = llama_model_get_vocab(model) else {
+    print("Failed to get vocab")
+    exit(1)
+}
+
 var tokens = tokenize(text: prompt, add_bos: true)
 
 let n_kv_req = UInt32(tokens.count) + UInt32((n_len - Int(tokens.count)) * n_parallel)
@@ -41,7 +46,7 @@ context_params.n_batch = UInt32(max(n_len, n_parallel))
 context_params.n_threads = 8
 context_params.n_threads_batch = 8
 
-let context = llama_new_context_with_model(model, context_params)
+let context = llama_init_from_model(model, context_params)
 guard context != nil else {
     print("Failed to initialize context")
     exit(1)
@@ -141,7 +146,7 @@ while n_cur <= n_len {
         let new_token_id = llama_sampler_sample(smpl, context, i_batch[i])
 
         // is it an end of stream? -> mark the stream as finished
-        if llama_vocab_is_eog(model, new_token_id) || n_cur == n_len {
+        if llama_vocab_is_eog(vocab, new_token_id) || n_cur == n_len {
             i_batch[i] = -1
             // print("")
             if n_parallel > 1 {
@@ -207,7 +212,7 @@ private func tokenize(text: String, add_bos: Bool) -> [llama_token] {
     let utf8Count = text.utf8.count
     let n_tokens = utf8Count + (add_bos ? 1 : 0)
     let tokens = UnsafeMutablePointer<llama_token>.allocate(capacity: n_tokens)
-    let tokenCount = llama_tokenize(model, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, /*special tokens*/ false)
+    let tokenCount = llama_tokenize(vocab, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, /*special tokens*/ false)
     var swiftTokens: [llama_token] = []
     for i in 0 ..< tokenCount {
         swiftTokens.append(tokens[Int(i)])
@@ -218,12 +223,12 @@ private func tokenize(text: String, add_bos: Bool) -> [llama_token] {
 
 private func token_to_piece(token: llama_token, buffer: inout [CChar]) -> String? {
     var result = [CChar](repeating: 0, count: 8)
-    let nTokens = llama_token_to_piece(model, token, &result, Int32(result.count), 0, false)
+    let nTokens = llama_token_to_piece(vocab, token, &result, Int32(result.count), 0, false)
     if nTokens < 0 {
         let actualTokensCount = -Int(nTokens)
         result = .init(repeating: 0, count: actualTokensCount)
         let check = llama_token_to_piece(
-            model,
+            vocab,
             token,
             &result,
             Int32(result.count),

examples/batched.swift/Sources/main.swift

@@ -24,6 +24,7 @@ func llama_batch_add(_ batch: inout llama_batch, _ id: llama_token, _ pos: llama
 actor LlamaContext {
     private var model: OpaquePointer
     private var context: OpaquePointer
+    private var vocab: OpaquePointer
     private var sampling: UnsafeMutablePointer<llama_sampler>
     private var batch: llama_batch
     private var tokens_list: [llama_token]
@@ -47,6 +48,7 @@ actor LlamaContext {
         self.sampling = llama_sampler_chain_init(sparams)
         llama_sampler_chain_add(self.sampling, llama_sampler_init_temp(0.4))
         llama_sampler_chain_add(self.sampling, llama_sampler_init_dist(1234))
+        vocab = llama_model_get_vocab(model)
     }
 
     deinit {
@@ -79,7 +81,7 @@ actor LlamaContext {
         ctx_params.n_threads       = Int32(n_threads)
         ctx_params.n_threads_batch = Int32(n_threads)
 
-        let context = llama_new_context_with_model(model, ctx_params)
+        let context = llama_init_from_model(model, ctx_params)
         guard let context else {
             print("Could not load context!")
             throw LlamaError.couldNotInitializeContext
@@ -151,7 +153,7 @@ actor LlamaContext {
 
         new_token_id = llama_sampler_sample(sampling, context, batch.n_tokens - 1)
 
-        if llama_vocab_is_eog(model, new_token_id) || n_cur == n_len {
+        if llama_vocab_is_eog(vocab, new_token_id) || n_cur == n_len {
             print("\n")
             is_done = true
             let new_token_str = String(cString: temporary_invalid_cchars + [0])
@@ -297,7 +299,7 @@ actor LlamaContext {
         let utf8Count = text.utf8.count
         let n_tokens = utf8Count + (add_bos ? 1 : 0) + 1
         let tokens = UnsafeMutablePointer<llama_token>.allocate(capacity: n_tokens)
-        let tokenCount = llama_tokenize(model, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, false)
+        let tokenCount = llama_tokenize(vocab, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, false)
 
         var swiftTokens: [llama_token] = []
         for i in 0..<tokenCount {
@@ -316,15 +318,15 @@ actor LlamaContext {
         defer {
             result.deallocate()
         }
-        let nTokens = llama_token_to_piece(model, token, result, 8, 0, false)
+        let nTokens = llama_token_to_piece(vocab, token, result, 8, 0, false)
 
         if nTokens < 0 {
             let newResult = UnsafeMutablePointer<Int8>.allocate(capacity: Int(-nTokens))
             newResult.initialize(repeating: Int8(0), count: Int(-nTokens))
             defer {
                 newResult.deallocate()
             }
-            let nNewTokens = llama_token_to_piece(model, token, newResult, -nTokens, 0, false)
+            let nNewTokens = llama_token_to_piece(vocab, token, newResult, -nTokens, 0, false)
             let bufferPointer = UnsafeBufferPointer(start: newResult, count: Int(nNewTokens))
             return Array(bufferPointer)
         } else {

examples/llama.swiftui/llama.cpp.swift/LibLlama.swift

@@ -3353,6 +3353,8 @@ static void log_server_request(const httplib::Request & req, const httplib::Resp
         return;
     }
 
+    // reminder: this function is not covered by httplib's exception handler; if someone does more complicated stuff, think about wrapping it in try-catch
+
     LOG_INF("request: %s %s %s %d\n", req.method.c_str(), req.path.c_str(), req.remote_addr.c_str(), res.status);
 
     LOG_DBG("request:  %s\n", req.body.c_str());
@@ -3439,9 +3441,13 @@ int main(int argc, char ** argv) {
             message = "Unknown Exception";
         }
 
-        json formatted_error = format_error_response(message, ERROR_TYPE_SERVER);
-        LOG_WRN("got exception: %s\n", formatted_error.dump().c_str());
-        res_error(res, formatted_error);
+        try {
+            json formatted_error = format_error_response(message, ERROR_TYPE_SERVER);
+            LOG_WRN("got exception: %s\n", formatted_error.dump().c_str());
+            res_error(res, formatted_error);
+        } catch (const std::exception & e) {
+            LOG_ERR("got another exception: %s | while hanlding exception: %s\n", e.what(), message.c_str());
+        }
     });
 
     svr->set_error_handler([&res_error](const httplib::Request &, httplib::Response & res) {