From b044a0fe3ca0cbef9dd041edce3ebda8c501fae4 Mon Sep 17 00:00:00 2001 From: Wagner Bruna Date: Mon, 10 Feb 2025 03:08:22 -0300 Subject: [PATCH 1/4] vulkan: add environment variable GGML_VK_PREFER_HOST_MEMORY to avoid VRAM allocation (#11592) --- ggml/src/ggml-vulkan/ggml-vulkan.cpp | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp index d32ba4efb..512d3341e 100644 --- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp +++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp @@ -167,6 +167,7 @@ struct vk_device_struct { uint32_t subgroup_size; uint32_t shader_core_count; bool uma; + bool prefer_host_memory; bool float_controls_rte_fp16; bool subgroup_size_control; @@ -1294,7 +1295,9 @@ static vk_buffer ggml_vk_create_buffer_check(vk_device& device, size_t size, vk: static vk_buffer ggml_vk_create_buffer_device(vk_device& device, size_t size) { vk_buffer buf; try { - if (device->uma) { + if (device->prefer_host_memory) { + buf = ggml_vk_create_buffer(device, size, vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent, vk::MemoryPropertyFlagBits::eDeviceLocal); + } else if (device->uma) { // Fall back to host memory type buf = ggml_vk_create_buffer(device, size, vk::MemoryPropertyFlagBits::eDeviceLocal, vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent); } else { @@ -2199,6 +2202,9 @@ static vk_device ggml_vk_get_device(size_t idx) { device->physical_device = physical_devices[dev_num]; const std::vector ext_props = device->physical_device.enumerateDeviceExtensionProperties(); + const char* GGML_VK_PREFER_HOST_MEMORY = getenv("GGML_VK_PREFER_HOST_MEMORY"); + device->prefer_host_memory = GGML_VK_PREFER_HOST_MEMORY != nullptr; + bool fp16_storage = false; bool fp16_compute = false; bool maintenance4_support = false; From c2a67efe38e6782c0217e1de3edc68de6951612b Mon Sep 17 00:00:00 2001 From: Danny Milosavljevic Date: Mon, 10 Feb 2025 07:17:21 +0100 Subject: [PATCH 2/4] vulkan: Make Vulkan optional at runtime (#11493). (#11494) Co-authored-by: Jeff Bolz --- ggml/include/ggml-vulkan.h | 2 -- ggml/src/ggml-vulkan/ggml-vulkan.cpp | 16 ++++++++++------ 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/ggml/include/ggml-vulkan.h b/ggml/include/ggml-vulkan.h index 53cdba072..ed5ea5f79 100644 --- a/ggml/include/ggml-vulkan.h +++ b/ggml/include/ggml-vulkan.h @@ -10,8 +10,6 @@ extern "C" { #define GGML_VK_NAME "Vulkan" #define GGML_VK_MAX_DEVICES 16 -GGML_BACKEND_API void ggml_vk_instance_init(void); - // backend API GGML_BACKEND_API ggml_backend_t ggml_backend_vk_init(size_t dev_num); diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp index 512d3341e..bffe95086 100644 --- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp +++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp @@ -2793,14 +2793,12 @@ static void ggml_vk_print_gpu_info(size_t idx) { static bool ggml_vk_instance_validation_ext_available(const std::vector& instance_extensions); static bool ggml_vk_instance_portability_enumeration_ext_available(const std::vector& instance_extensions); -void ggml_vk_instance_init() { +static void ggml_vk_instance_init() { if (vk_instance_initialized) { return; } VK_LOG_DEBUG("ggml_vk_instance_init()"); - vk_instance_initialized = true; - uint32_t api_version = vk::enumerateInstanceVersion(); if (api_version < VK_API_VERSION_1_2) { @@ -2851,6 +2849,7 @@ void ggml_vk_instance_init() { GGML_LOG_DEBUG("ggml_vulkan: Validation layers enabled\n"); } vk_instance.instance = vk::createInstance(instance_create_info); + vk_instance_initialized = true; size_t num_available_devices = vk_instance.instance.enumeratePhysicalDevices().size(); @@ -2875,7 +2874,7 @@ void ggml_vk_instance_init() { // Make sure at least one device exists if (devices.empty()) { std::cerr << "ggml_vulkan: Error: No devices found." << std::endl; - GGML_ABORT("fatal error"); + return; } // Default to using all dedicated GPUs @@ -8350,8 +8349,13 @@ ggml_backend_reg_t ggml_backend_vk_reg() { /* .iface = */ ggml_backend_vk_reg_i, /* .context = */ nullptr, }; - - return ® + try { + ggml_vk_instance_init(); + return ® + } catch (const vk::SystemError& e) { + VK_LOG_DEBUG("ggml_backend_vk_reg() -> Error: System error: " << e.what()); + return nullptr; + } } // Extension availability From 9ac3457b39c78c5eb103280e08fb6163642484ff Mon Sep 17 00:00:00 2001 From: pascal-lc <49066376+pascal-lc@users.noreply.github.com> Date: Mon, 10 Feb 2025 16:05:57 +0800 Subject: [PATCH 3/4] Update README.md [no ci] (#11781) typo: `\` -> `/` Change the UNIX path separator to` \`. --- examples/main/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/main/README.md b/examples/main/README.md index 46f92eb7a..ceaed42f6 100644 --- a/examples/main/README.md +++ b/examples/main/README.md @@ -37,7 +37,7 @@ Once downloaded, place your model in the models folder in llama.cpp. ##### Infinite text from a starting prompt (you can use `Ctrl-C` to stop it): ```bash -./llama-cli -m models\gemma-1.1-7b-it.Q4_K_M.gguf --ignore-eos -n -1 +./llama-cli -m models/gemma-1.1-7b-it.Q4_K_M.gguf --ignore-eos -n -1 ``` ### Windows: From d7b31a9d84297b493a61c9a8ee3a458e7ccc64a7 Mon Sep 17 00:00:00 2001 From: Olivier Chafik Date: Mon, 10 Feb 2025 09:34:09 +0000 Subject: [PATCH 4/4] sync: minja (https://github.com/google/minja/commit/a72057e5190de2c612d4598bb10b4bfd0f53011f) (#11774) --- common/chat-template.hpp | 28 +++++++++++++++++++++------- common/minja.hpp | 33 ++++++++++++++++++++++++--------- 2 files changed, 45 insertions(+), 16 deletions(-) diff --git a/common/chat-template.hpp b/common/chat-template.hpp index 0e88fb361..882ba41bd 100644 --- a/common/chat-template.hpp +++ b/common/chat-template.hpp @@ -249,16 +249,30 @@ class chat_template { inputs.add_generation_prompt = false; full = apply(inputs); } - - if (full.find(prefix) != 0) { - if (prefix.rfind(eos_token_) == prefix.size() - eos_token_.size()) { - prefix = prefix.substr(0, prefix.size() - eos_token_.size()); + auto eos_pos_last = full.rfind(eos_token_); + if (eos_pos_last == prefix.size() - eos_token_.size() || + (full[full.size() - 1] == '\n' && (eos_pos_last == full.size() - eos_token_.size() - 1))) { + full = full.substr(0, eos_pos_last); + } + size_t common_prefix_length = 0; + for (size_t i = 0; i < prefix.size() && i < full.size(); ++i) { + if (prefix[i] != full[i]) { + break; } + if (prefix[i] == '<') { + // DeepSeek R1's template (as of 20250209) adds a trailing if add_generation_prompt, + // but it removes thinking tags for past messages. + // The prefix and full strings diverge at vs. <｜tool▁calls▁begin｜>, we avoid consuming the leading <. + continue; + } + common_prefix_length = i + 1; } - if (full.find(prefix) != 0) { + auto example = full.substr(common_prefix_length); + if (example.find("tool_name") == std::string::npos && example.find("some_value") == std::string::npos) { fprintf(stderr, "Failed to infer a tool call example (possible template bug)\n"); + } else { + tool_call_example_ = example; } - tool_call_example_ = full.substr(prefix.size()); } } catch (const std::exception & e) { fprintf(stderr, "Failed to generate tool call example: %s\n", e.what()); @@ -363,7 +377,7 @@ class chat_template { if (polyfill_tools) { adjusted_messages = add_system(inputs.messages, "You can call any of the following tools to satisfy the user's requests: " + minja::Value(inputs.tools).dump(2, /* to_json= */ true) + - (!polyfill_tool_call_example || tool_call_example_.empty() ? "" : "\n\nExample tool call syntax:\n\n" + tool_call_example_)); + (!polyfill_tool_call_example || tool_call_example_.empty() ? "" : "\n\nExample tool call syntax:\n\n" + tool_call_example_ + "\n\n")); } else { adjusted_messages = inputs.messages; } diff --git a/common/minja.hpp b/common/minja.hpp index c304b5c66..c58dd66e0 100644 --- a/common/minja.hpp +++ b/common/minja.hpp @@ -1385,6 +1385,13 @@ static std::string strip(const std::string & s) { return s.substr(start, end - start + 1); } +static std::string capitalize(const std::string & s) { + if (s.empty()) return s; + auto result = s; + result[0] = std::toupper(result[0]); + return result; +} + static std::string html_escape(const std::string & s) { std::string result; result.reserve(s.size()); @@ -1462,6 +1469,9 @@ public: if (method->get_name() == "strip") { vargs.expectArgs("strip method", {0, 0}, {0, 0}); return Value(strip(str)); + } else if (method->get_name() == "capitalize") { + vargs.expectArgs("capitalize method", {0, 0}, {0, 0}); + return Value(capitalize(str)); } else if (method->get_name() == "endswith") { vargs.expectArgs("endswith method", {1, 1}, {0, 0}); auto suffix = vargs.args[0].get(); @@ -1792,7 +1802,7 @@ private: auto left = parseStringConcat(); if (!left) throw std::runtime_error("Expected left side of 'logical compare' expression"); - static std::regex compare_tok(R"(==|!=|<=?|>=?|in\b|is\b|not[\r\n\s]+in\b)"); + static std::regex compare_tok(R"(==|!=|<=?|>=?|in\b|is\b|not\s+in\b)"); static std::regex not_tok(R"(not\b)"); std::string op_str; while (!(op_str = consumeToken(compare_tok)).empty()) { @@ -2171,7 +2181,7 @@ private: using TemplateTokenIterator = TemplateTokenVector::const_iterator; std::vector parseVarNames() { - static std::regex varnames_regex(R"(((?:\w+)(?:[\r\n\s]*,[\r\n\s]*(?:\w+))*)[\r\n\s]*)"); + static std::regex varnames_regex(R"(((?:\w+)(?:\s*,\s*(?:\w+))*)\s*)"); std::vector group; if ((group = consumeTokenGroups(varnames_regex)).empty()) throw std::runtime_error("Expected variable names"); @@ -2194,13 +2204,13 @@ private: } TemplateTokenVector tokenize() { - static std::regex comment_tok(R"(\{#([-~]?)([\s\S\r\n]*?)([-~]?)#\})"); + static std::regex comment_tok(R"(\{#([-~]?)([\s\S]*?)([-~]?)#\})"); static std::regex expr_open_regex(R"(\{\{([-~])?)"); - static std::regex block_open_regex(R"(^\{%([-~])?[\s\n\r]*)"); + static std::regex block_open_regex(R"(^\{%([-~])?\s*)"); static std::regex block_keyword_tok(R"((if|else|elif|endif|for|endfor|generation|endgeneration|set|endset|block|endblock|macro|endmacro|filter|endfilter|break|continue)\b)"); static std::regex non_text_open_regex(R"(\{\{|\{%|\{#)"); - static std::regex expr_close_regex(R"([\s\n\r]*([-~])?\}\})"); - static std::regex block_close_regex(R"([\s\n\r]*([-~])?%\})"); + static std::regex expr_close_regex(R"(\s*([-~])?\}\})"); + static std::regex block_close_regex(R"(\s*([-~])?%\})"); TemplateTokenVector tokens; std::vector group; @@ -2284,7 +2294,7 @@ private: auto post_space = parseBlockClose(); tokens.push_back(std::make_unique(location, pre_space, post_space)); } else if (keyword == "set") { - static std::regex namespaced_var_regex(R"((\w+)[\s\n\r]*\.[\s\n\r]*(\w+))"); + static std::regex namespaced_var_regex(R"((\w+)\s*\.\s*(\w+))"); std::string ns; std::vector var_names; @@ -2336,6 +2346,11 @@ private: throw std::runtime_error("Unexpected block: " + keyword); } } else if (std::regex_search(it, end, match, non_text_open_regex)) { + if (!match.position()) { + if (match[0] != "{#") + throw std::runtime_error("Internal error: Expected a comment"); + throw std::runtime_error("Missing end of comment tag"); + } auto text_end = it + match.position(); text = std::string(it, text_end); it = text_end; @@ -2400,7 +2415,7 @@ private: auto text = text_token->text; if (post_space == SpaceHandling::Strip) { - static std::regex trailing_space_regex(R"((\s|\r|\n)+$)"); + static std::regex trailing_space_regex(R"(\s+$)"); text = std::regex_replace(text, trailing_space_regex, ""); } else if (options.lstrip_blocks && it != end) { auto i = text.size(); @@ -2410,7 +2425,7 @@ private: } } if (pre_space == SpaceHandling::Strip) { - static std::regex leading_space_regex(R"(^(\s|\r|\n)+)"); + static std::regex leading_space_regex(R"(^\s+)"); text = std::regex_replace(text, leading_space_regex, ""); } else if (options.trim_blocks && (it - 1) != begin && !dynamic_cast((*(it - 2)).get())) { if (text.length() > 0 && text[0] == '\n') {