Merge branch 'ggml-org:master' into i8mm-ci

Author: Rohanjames1997

.github/workflows/build.yml

@@ -1390,14 +1390,10 @@ jobs:
     strategy:
       matrix:
         arch: [x86, aarch64]
-        cann:
-          - '8.3.rc1.alpha001-910b-openeuler22.03-py3.11'
-        chip_type:
-          - '910b'
-        build:
-          - 'Release'
+        chip_type: ['910b', '310p']
+        build: ['Release']
     runs-on: ${{ matrix.arch == 'aarch64' && 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
-    container: ascendai/cann:${{ matrix.cann }}
+    container: ascendai/cann:${{ matrix.chip_type == '910b' &&  '8.3.rc1.alpha001-910b-openeuler22.03-py3.11' || '8.2.rc1-310p-openeuler22.03-py3.11' }}
     steps:
       - name: Checkout
         uses: actions/checkout@v4

.github/workflows/release.yml

@@ -698,10 +698,9 @@ jobs:
       matrix:
         arch: [x86, aarch64]
         chip_type: ['910b', '310p']
-        build:
-          - 'Release'
+        build: ['Release']
     runs-on: ${{ matrix.arch == 'aarch64' && 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
-    container: ascendai/cann:${{ matrix.chip_type == '910b' &&  '8.3.rc1.alpha001-910b-openeuler22.03-py3.11' || '8.3.rc1.alpha001-310p-openeuler22.03-py3.11' }}
+    container: ascendai/cann:${{ matrix.chip_type == '910b' &&  '8.3.rc1.alpha001-910b-openeuler22.03-py3.11' || '8.2.rc1-310p-openeuler22.03-py3.11' }}
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -737,7 +736,7 @@ jobs:
         uses: actions/upload-artifact@v4
         with:
           path: llama-${{ steps.tag.outputs.name }}-bin-${{ matrix.chip_type }}-openEuler-${{ matrix.arch }}.zip
-          name: llama-${{ steps.tag.outputs.name }}-bin-${{ matrix.chip_type }}-openEuler-${{ matrix.arch }}
+          name: llama-bin-${{ matrix.chip_type }}-openEuler-${{ matrix.arch }}.zip
 
   release:
     if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}

common/CMakeLists.txt

@@ -50,6 +50,8 @@ add_library(${TARGET} STATIC
     base64.hpp
     chat-parser.cpp
     chat-parser.h
+    chat-parser-xml-toolcall.h
+    chat-parser-xml-toolcall.cpp
     chat.cpp
     chat.h
     common.cpp

common/chat-parser-xml-toolcall.cpp

@@ -0,0 +1,45 @@
+#pragma once
+
+#include "chat.h"
+
+#include <nlohmann/json.hpp>
+
+#include <optional>
+#include <string>
+#include <vector>
+
+
+// Sample config:
+// MiniMax-M2 (left): <minimax:tool_call>\n<invoke name="tool-name">\n<parameter name="key">value</parameter>\n...</invoke>\n...</minimax:tool_call>
+// GLM 4.5   (right): <tool_call>function_name\n<arg_key>key</arg_key>\n<arg_value>value</arg_value>\n</tool_call>
+struct xml_tool_call_format {
+    std::string scope_start; // <minimax:tool_call>\n  // \n                      // can be empty
+    std::string tool_start;  // <invoke name=\"        // <tool_call>
+    std::string tool_sep;    // \">\n                  // \n                      // can be empty only for parse_xml_tool_calls
+    std::string key_start;   // <parameter name=\"     // <arg_key>
+    std::string key_val_sep; // \">                    // </arg_key>\n<arg_value>
+    std::string val_end;     // </parameter>\n         // </arg_value>\n
+    std::string tool_end;    // </invoke>\n            // </tool_call>\n
+    std::string scope_end;   // </minimax:tool_call>   //                         // can be empty
+    // Set this if there can be dynamic spaces inside key_val_sep.
+    // e.g. key_val_sep=</arg_key> key_val_sep2=<arg_value> for GLM4.5
+    std::optional<std::string> key_val_sep2 = std::nullopt;
+    // Set true if argval should only be raw string. e.g. Hello "world" hi
+    // Set false if argval should only be json string. e.g. "Hello \"world\" hi"
+    // Defaults to std::nullopt, both will be allowed.
+    std::optional<bool> raw_argval = std::nullopt;
+    std::optional<std::string> last_val_end = std::nullopt;
+    std::optional<std::string> last_tool_end = std::nullopt;
+    bool trim_raw_argval = false;
+    bool allow_toolcall_in_think = false; // TODO: UNTESTED!!!
+};
+
+// make a GBNF that accept any strings except those containing any of the forbidden strings.
+std::string make_gbnf_excluding(std::vector<std::string> forbids);
+
+/**
+ * Build grammar for xml-style tool call
+ * form.scope_start and form.scope_end can be empty.
+ * Requires data.format for model-specific hacks.
+ */
+void build_grammar_xml_tool_call(common_chat_params & data, const nlohmann::ordered_json & tools, const struct xml_tool_call_format & form);

common/chat-parser-xml-toolcall.h

@@ -1,6 +1,7 @@
 #pragma once
 
 #include "chat.h"
+#include "chat-parser-xml-toolcall.h"
 #include "json-partial.h"
 #include "regex-partial.h"
 
@@ -119,5 +120,14 @@ class common_chat_msg_parser {
         const std::vector<std::vector<std::string>> & content_paths = {}
     );
 
+    /**
+     * Parse XML-Style tool call for given xml_tool_call_format. Return false for invalid syntax and get the position untouched.
+     * form.scope_start, form.tool_sep and form.scope_end can be empty.
+     */
+    bool try_consume_xml_tool_calls(const struct xml_tool_call_format & form);
+
+    // Parse content uses reasoning and XML-Style tool call
+    void consume_reasoning_with_xml_tool_calls(const struct xml_tool_call_format & form, const std::string & start_think = "<think>", const std::string & end_think = "</think>");
+
     void clear_tools();
 };