@osanseviero: Gemma 4 MTP 现已正式合并到 llama.cpp，这意味着你可以使用 Gemma 4 QAT + MTP 来实现轻量级且超快的…

Gemma 4 MTP 已正式合并到 llama.cpp 中。这意味着您可以使用 Gemma 4 QAT + MTP 构建轻量级且超快速的设置。期待看到社区用它构建的项目 https://t.co/1te7tgdi2H — # ggml-org/llama.cpp 来源：https://github.com/ggml-org/llama.cpp # llama.cpp llama 许可证：MIT (https://opensource.org/licenses/MIT) 发布版 (https://github.com/ggml-org/llama.cpp/releases) 服务器 (https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml) Docker (https://github.com/ggml-org/llama.cpp/actions/workflows/docker.yml) Winget (https://github.com/ggml-org/llama.cpp/actions/workflows/winget.yml) 宣言 (https://github.com/ggml-org/llama.cpp/discussions/205) / ggml (https://github.com/ggml-org/ggml) / 操作 (https://github.com/ggml-org/llama.cpp/blob/master/docs/ops.md) C/C++ 中的 LLM 推理 ## 最近的 API 变更 - libllama API 的变更日志 (https://github.com/ggml-org/llama.cpp/issues/9289) - llama-server REST API 的变更日志 (https://github.com/ggml-org/llama.cpp/issues/9291) ## 热门话题 - Hugging Face 缓存迁移：使用 -hf 下载的模型现在存储在标准的 Hugging Face 缓存目录中，从而能够与其他 HF 工具共享。 - 指南：使用 llama.cpp 的新 WebUI (https://github.com/ggml-org/llama.cpp/discussions/16938) - 指南：使用 llama.cpp 运行 gpt-oss (https://github.com/ggml-org/llama.cpp/discussions/15396) - [反馈] 为 llama.cpp 提供更好的打包以支持下游消费者 🤗 - 已添加对采用原生 MXFP4 格式的 gpt-oss 模型的支持 | PR (https://github.com/ggml-org/llama.cpp/pull/15091) | 与 NVIDIA 的合作 (https://blogs.nvidia.com/blog/rtx-ai-garage-openai-oss) | 评论 (https://github.com/ggml-org/llama.cpp/discussions/15095) - llama-server 中加入了多模态支持：#12898 (https://github.com/ggml-org/llama.cpp/pull/12898) | 文档 - 用于 FIM 补全的 VS Code 扩展：https://github.com/ggml-org/llama.vscode - 用于 FIM 补全的 Vim/Neovim 插件：https://github.com/ggml-org/llama.vim - Hugging Face 推理端点现在原生支持 GGUF！https://github.com/ggml-org/llama.cpp/discussions/9669 - Hugging Face GGUF 编辑器：讨论 (https://github.com/ggml-org/llama.cpp/discussions/9268) | 工具 (https://huggingface.co/spaces/CISCai/gguf-editor) - 浏览器中现已支持 WebGPU，请在此处查看介绍它的博客/演示 (https://reeselevine.github.io/llamas-on-the-web/)。 –– ## 快速开始 开始使用 llama.cpp 非常简单。以下是几种在您机器上安装它的方法： - 使用 brew、nix 或 winget 安装 llama.cpp - 使用 Docker 运行——请参阅我们的 Docker 文档 - 从发布页面 (https://github.com/ggml-org/llama.cpp/releases) 下载预构建的二进制文件 - 克隆此存储库并从源代码构建——请查看我们的构建指南 安装完成后，您需要一个模型来使用。请前往获取和量化模型部分了解更多信息。 示例命令： sh # 使用本地模型文件 llama-cli -m my_model.gguf # 或者直接从 Hugging Face 下载并运行模型 llama-cli -hf ggml-org/gemma-3-1b-it-GGUF # 启动兼容 OpenAI 的 API 服务器 llama-server -hf ggml-org/gemma-3-1b-it-GGUF ## 描述 llama.cpp 的主要目标是实现 LLM 推理，只需最少的设置，并在各种硬件（本地和云端）上提供最先进的性能。 - 纯 C/C++ 实现，无任何依赖 - Apple silicon 是一等公民——通过 ARM NEON、Accelerate 和 Metal 框架进行了优化 - 支持 x86 架构的 AVX、AVX2、AVX512 和 AMX - 支持 RISC-V 架构的 RVV、ZVFH、ZFH、ZICBOP 和 ZIHINTPAUSE - 1.5 位、2 位、3 位、4 位、5 位、6 位和 8 位整数量化，实现更快的推理和更少的内存使用 - 自定义 CUDA 内核，用于在 NVIDIA GPU 上运行 LLM（通过 HIP 支持 AMD GPU，通过 MUSA 支持摩尔线程 GPU） - 支持 Vulkan 和 SYCL 后端 - CPU+GPU 混合推理，可部分加速超出总 VRAM 容量的模型 llama.cpp 项目是开发 ggml (https://github.com/ggml-org/ggml) 库新特性的主要试验场。 模型 通常，以下基础模型的微调版本也受支持。添加新模型支持的说明：HOWTO-add-model.md #### 纯文本 - [X] LLaMA 🦙 - [x] LLaMA 2 🦙🦙 - [x] LLaMA 3 🦙🦙🦙 - [X] Mistral 7B (https://huggingface.co/mistralai/Mistral-7B-v0.1) - [x] Mixtral MoE (https://huggingface.co/models?search=mistral-ai/Mixtral) - [x] DBRX (https://huggingface.co/databricks/dbrx-instruct) - [x] Jamba (https://huggingface.co/ai21labs) - [X] Falcon (https://huggingface.co/models?search=tiiuae/falcon) - [X] Chinese LLaMA / Alpaca (https://github.com/ymcui/Chinese-LLaMA-Alpaca) 和 Chinese LLaMA-2 / Alpaca-2 (https://github.com/ymcui/Chinese-LLaMA-Alpaca-2) - [X] Vigogne（法语）(https://github.com/bofenghuang/vigogne) - [X] BERT (https://github.com/ggml-org/llama.cpp/pull/5423) - [X] Koala (https://bair.berkeley.edu/blog/2023/04/03/koala/) - [X] Baichuan 1 & 2 (https://huggingface.co/models?search=baichuan-inc/Baichuan) + 衍生模型 (https://huggingface.co/hiyouga/baichuan-7b-sft) - [X] Aquila 1 & 2 (https://huggingface.co/models?search=BAAI/Aquila) - [X] Starcoder 模型 (https://github.com/ggml-org/llama.cpp/pull/3187) - [X] Refact (https://huggingface.co/smallcloudai/Refact-1_6B-fim) - [X] MPT (https://github.com/ggml-org/llama.cpp/pull/3417) - [X] Bloom (https://github.com/ggml-org/llama.cpp/pull/3553) - [x] Yi 模型 (https://huggingface.co/models?search=01-ai/Yi) - [X] StableLM 模型 (https://huggingface.co/stabilityai) - [x] Deepseek 模型 (https://huggingface.co/models?search=deepseek-ai/deepseek) - [x] Qwen 模型 (https://huggingface.co/models?search=Qwen/Qwen) - [x] PLaMo-13B (https://github.com/ggml-org/llama.cpp/pull/3557) - [x] Phi 模型 (https://huggingface.co/models?search=microsoft/phi) - [x] PhiMoE (https://github.com/ggml-org/llama.cpp/pull/11003) - [x] GPT-2 (https://huggingface.co/gpt2) - [x] Orion 14B (https://github.com/ggml-org/llama.cpp/pull/5118) - [x] InternLM2 (https://huggingface.co/models?search=internlm2) - [x] CodeShell (https://github.com/WisdomShell/codeshell) - [x] Gemma (https://ai.google.dev/gemma) - [x] Mamba (https://github.com/state-spaces/mamba) - [x] Grok-1 (https://huggingface.co/keyfan/grok-1-hf) - [x] Xverse (https://huggingface.co/models?search=xverse) - [x] Command-R 模型 (https://huggingface.co/models?search=CohereForAI/c4ai-command-r) - [x] SEA-LION (https://huggingface.co/models?search=sea-lion) - [x] GritLM-7B (https://huggingface.co/GritLM/GritLM-7B) + GritLM-8x7B (https://huggingface.co/GritLM/GritLM-8x7B) - [x] OLMo (https://allenai.org/olmo) - [x] OLMo 2 (https://allenai.org/olmo) - [x] OLMoE (https://huggingface.co/allenai/OLMoE-1B-7B-0924) - [x] Granite 模型 (https://huggingface.co/collections/ibm-granite/granite-code-models-6624c5cec322e4c148c8b330) - [x] GPT-NeoX (https://github.com/EleutherAI/gpt-neox) + Pythia (https://github.com/EleutherAI/pythia) - [x] Snowflake-Arctic MoE (https://huggingface.co/collections/Snowflake/arctic-66290090abe542894a5ac520) - [x] Smaug (https://huggingface.co/models?search=Smaug) - [x] Poro 34B (https://huggingface.co/LumiOpen/Poro-34B) - [x] Bitnet b1.58 模型 (https://huggingface.co/1bitLLM) - [x] Flan T5 (https://huggingface.co/models?search=flan-t5) - [x] Open Elm 模型 (https://huggingface.co/collections/apple/openelm-instruct-models-6619ad295d7ae9f868b759ca) - [x] ChatGLM3-6b (https://huggingface.co/THUDM/chatglm3-6b) + ChatGLM4-9b (https://huggingface.co/THUDM/glm-4-9b) + GLMEdge-1.5b (https://huggingface.co/THUDM/glm-edge-1.5b-chat) + GLMEdge-4b (https://huggingface.co/THUDM/glm-edge-4b-chat) - [x] GLM-4-0414 (https://huggingface.co/collections/THUDM/glm-4-0414-67f3cbcb34dd9d252707cb2e) - [x] SmolLM (https://huggingface.co/collections/HuggingFaceTB/smollm-6695016cad7167254ce15966) - [x] EXAONE-3.0-7.8B-Instruct (https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct) - [x] FalconMamba 模型 (https://huggingface.co/collections/tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a) - [x] Jais (https://huggingface.co/inceptionai/jais-13b-chat) - [x] Bielik-11B-v2.3 (https://huggingface.co/collections/speakleash/bielik-11b-v23-66ee813238d9b526a072408a) - [x] RWKV-7 (https://huggingface.co/collections/shoumenchougou/rwkv7-gxx-gguf) - [x] RWKV-6 (https://github.com/BlinkDL/RWKV-LM) - [x] QRWKV-6 (https://huggingface.co/recursal/QRWKV6-32B-Instruct-Preview-v0.1) - [x] GigaChat-20B-A3B (https://huggingface.co/ai-sage/GigaChat-20B-A3B-instruct) - [X] Trillion-7B-preview (https://huggingface.co/trillionlabs/Trillion-7B-preview) - [x] Ling 模型 (https://huggingface.co/collections/inclusionAI/ling-67c51c85b34a7ea0aba94c32) - [x] LFM2 模型 (https://huggingface.co/collections/LiquidAI/lfm2-686d721927015b2ad73eaa38) - [x] Hunyuan 模型 (https://huggingface.co/collections/tencent/hunyuan-dense-model-6890632cda26b19119c9c5e7) - [x] BailingMoeV2（Ling 2.0）模型 (https://huggingface.co/collections/inclusionAI/ling-v2-68bf1dd2fc34c306c1fa6f86) - [x] Mellum 模型 (https://huggingface.co/JetBrains/models?search=mellum) #### 多模态 - [x] LLaVA 1.5 模型 (https://huggingface.co/collections/liuhaotian/llava-15-653aac15d994e992e2677a7e)，LLaVA 1.6 模型 (https://huggingface.co/collections/liuhaotian/llava-16-65b9e40155f60fd046a5ccf2) - [x] BakLLaVA (https://huggingface.co/models?search=SkunkworksAI/Bakllava) - [x] Obsidian (https://huggingface.co/NousResearch/Obsidian-3B-V0.5) - [x] ShareGPT4V (https://huggingface.co/models?search=Lin-Chen/ShareGPT4V) - [x] MobileVLM 1.7B/3B 模型 (https://huggingface.co/models?search=mobileVLM) - [x] Yi-VL (https://huggingface.co/models?search=Yi-VL) - [x] Mini CPM (https://huggingface.co/models?search=MiniCPM) - [x] Moondream (https://huggingface.co/vikhyatk/moondream2) - [x] Bunny (https://github.com/BAAI-DCAI/Bunny) - [x] GLM-EDGE (https://huggingface.co/models?search=glm-edge) - [x] Qwen2-VL (https://huggingface.co/collections/Qwen/qwen2-vl-66cee7455501d7126940800d) - [x] LFM2-VL (https://huggingface.co/collections/LiquidAI/lfm2-vl-68963bbc84a610f7638d5ffa) 绑定 - Python：ddh0/easy-llama (https://github.com/ddh0/easy-llama) - Python：abetlen/llama-cpp-python (https://github.com/abetlen/llama-cpp-python) - Go：go-skynet/go-llama.cpp (https://github.com/go-skynet/go-llama.cpp) - Node.js：withcatai/node-llama-cpp (https://github.com/withcatai/node-llama-cpp) - JS/TS（llama.cpp 服务器客户端）：lgrammel/modelfusion (https://modelfusion.dev/integration/model-provider/llamacpp) - JS/TS（可编程提示引擎 CLI）：offline-ai/cli (https://github.com/offline-ai/cli) - JavaScript/Wasm（可在浏览器中运行）：tangledgroup/llama-cpp-wasm (https://github.com/tangledgroup/llama-cpp-wasm) - Typescript/Wasm（更友好的 API，可在 npm 上获取）：ngxson/wllama (https://github.com/ngxson/wllama) - Ruby：yoshoku/llama_cpp.rb (https://github.com/yoshoku/llama_cpp.rb) - Ruby：docusealco/rllama (https://github.com/docusealco/rllama) - Rust（功能更多）：edgenai/llama_cpp-rs (https://github.com/edgenai/llama_cpp-rs) - Rust（更友好的 API）：mdrokz/rust-llama.cpp (https://github.com/mdrokz/rust-llama.cpp) - Rust（更直接的绑定）：utilityai/llama-cpp-rs (https://github.com/utilityai/llama-cpp-rs) - Rust（从 crates.io 自动构建）：ShelbyJenkins/llm_client (https://github.com/ShelbyJenkins/llm_client) - C#/.NET：SciSharp/LLamaSharp (https://github.com/SciSharp/LLamaSharp) - C#/VB.NET（功能更多——社区许可证）：LM-Kit.NET (https://docs.lm-kit.com/lm-kit-net/index.html) - Scala 3：donderom/llm4s (https://github.com/donderom/llm4s) - Clojure：phronmophobic/llama.clj (https://github.com/phronmophobic/llama.clj) - React Native：mybigday/llama.rn (https://github.com/mybigday/llama.rn) - Java：kherud/java-llama.cpp (https://github.com/kherud/java-llama.cpp) - Java：QuasarByte/llama-cpp-jna (https://github.com/QuasarByte/llama-cpp-jna) - Zig：deins/llama.cpp.zig (https://github.com/Deins/llama.cpp.zig) - Flutter/Dart：netdur/llama_cpp_dart (https://github.com/netdur/llama_cpp_dart) - Flutter：xuegao-tzx/Fllama (https://github.com/xuegao-tzx/Fllama) - PHP（基于 llama.cpp 的 API 绑定和功能）：distantmagic/resonance (https://github.com/distantmagic/resonance)（更多信息）(https://github.com/ggml-org/llama.cpp/pull/6326) - Guile Scheme：guile_llama_cpp (https://savannah.nongnu.org/projects/guile-llama-cpp) - Swift srgtuszy/llama-cpp-swift (https://github.com/srgtuszy/llama-cpp-swift) - Swift ShenghaiWang/SwiftLlama (https://github.com/ShenghaiWang/SwiftLlama) - Delphi Embarcadero/llama-cpp-delphi (https://github.com/Embarcadero/llama-cpp-delphi) - Go（不需要 CGo）：hybridgroup/yzma (https://github.com/hybridgroup/yzma) - Android：llama.android 用户界面 （若要将某个项目列在此处，它应明确声明依赖于 llama.cpp） - AI Sublime Text 插件 (https://github.com/yaroslavyaroslav/OpenAI-sublime-text) (MIT) - BonzAI 应用 (https://apps.apple.com/us/app/bonzai-your-local-ai-agent/id6752847988)（专有） - cztomsik/ava (https://github.com/cztomsik/ava) (MIT) - Dot (https://github.com/alexpinel/Dot) (GPL) - eva (https://github.com/ylsdamxssjxxdd/eva) (MIT) - iohub/collama (https://github.com/iohub/coLLaMA) (Apache-2.0) - janhq/jan (https://github.com/janhq/jan) (AGPL) - johnbean393/Sidekick (https://github.com/johnbean393/Sidekick) (MIT) - KanTV (https://github.com/zhouwg/kantv?tab=readme-ov-file) (Apache-2.0) - KodiBot (https://github.com/firatkiral/kodibot) (GPL) - llama.vim (https://github.com/ggml-org/llama.vim) (MIT) - LARS (https://github.com/abgulati/LARS) (AGPL) - Llama Assistant (https://github.com/vietanhdev/llama-assistant) (GPL) - LlamaLib (https://github.com/undreamai/LlamaLib) (Apache-2.0) - LLMFarm (https://github.com/guinmoon/LLMFarm?tab=readme-ov-file) (MIT) - LLMUnity (https://github.com/undreamai/LLMUnity) (MIT) - LMStudio (https://lmstudio.ai/)（专有） - LocalAI (https://github.com/mudler/LocalAI) (MIT) - LostRuins/koboldcpp (https://github.com/LostRuins/koboldcpp) (AGPL) - MindMac (https://mindmac.app)（专有） - MindWorkAI/AI-Studio (https://github.com/MindWorkAI/AI-Studio) (FSL-1.1-MIT) - Mobile-Artificial-Intelligence/maid (https://github.com/Mobile-Artificial-Intelligence/maid) (MIT) - Mozilla-Ocho/llamafile (https://github.com/Mozilla-Ocho/llamafile) (Apache-2.0) - nat/openplayground (https://github.com/nat/openplayground) (MIT) - nomic-ai/gpt4all (https://github.com/nomic-ai/gpt4all) (MIT) - ollama/ollama (https://github.com/ollama/ollama) (MIT) - oobabooga/text-generation-webui (https://github.com/oobabooga/text-generation-webui) (AGPL) - PocketPal AI (https://github.com/a-ghorbani/pocketpal-ai) (MIT) - psugihara/FreeChat (https://github.com/psugihara/FreeChat) (MIT) - ptsochantaris/emeltal (https://github.com/ptsochantaris/emeltal) (MIT) - pythops/tenere (https://github.com/pythops/tenere) (AGPL) - ramalama (https://github.com/containers/ramalama) (MIT) - semperai/amica (https://github.com/semperai/amica) (MIT) - withcatai/catai (https://github.com/withcatai/catai) (MIT) - Autopen (https://github.com/blackhole89/autopen) (GPL) 工具 - akx/ggify (https://github.com/akx/ggify) – 从 Hugging Face Hub 下载 PyTorch 模型并转换为 GGML - akx/ollama-dl (https://github.com/akx/ollama-dl) – 从 Ollama 库下载模型以直接与 llama.cpp 一起使用 - crashr/gppm (https://github.com/crashr/gppm) – 启动 llama.cpp 实例，利用 NVIDIA Tesla P40 或 P100 GPU，降低空闲功耗 - gpustack/gguf-parser (https://github.com/gpustack/gguf-parser-go/tree/main/cmd/gguf-parser)