base on a fast cross platform AI inference engine 🤖 using Rust 🦀 and WebGPU 🎮 # crabml [](https://discord.gg/wbzqddT3QC) `crabml` is a llama.cpp compatible (and equally fast!) AI inference engine written in 🦀 **Rust**, which runs everywhere with the help of 🎮 **WebGPU**. ## Project Goals `crabml` is designed with the following objectives in mind: - 🤖 Focus solely on inference. - 🎮 Runs on browsers, desktops, and servers everywhere with the help of **WebGPU**. - ⏩ **SIMD**-accelerated inference on inexpensive hardware. - 💼 `mmap()` from day one, minimized memory requirement with various quantization support. - 👾 Hackable & embeddable. ## Supported Models `crabml` supports the following models in GGUF format: - 🦙 Llama - 🦙 CodeLlama - 🦙 Gemma - 〽️ Mistral - 🚄 On the way: Mistral MoE, Phi, QWen, StarCoder, Llava, and more! For more information, you can visit [How to Get GGUF Models](https://github.com/crabml/crabml/blob/main/docs/how-to-get-gguf-models.md) to learn how to download the GGUF files you need. ## Supported Quantization Methods `crabml` supports the following quantization methods on CPUs with SIMD acceleration for ARM (including Apple Silicon) and x86 architectures: | | Bits | Native CPU | NEON | AVX2 | RISC-V SIMD | WebGPU | | ---- | ------ | ---------- | ---- | ---- | ------ | ------- | | Q8_0 | 8 bits | ✅ | ✅ | ✅ | WIP | WIP | | Q6_K | 6 bits | ✅ | WIP | WIP | WIP | WIP | | Q5_0 | 5 bits | ✅ | WIP | WIP | WIP | WIP | | Q5_1 | 5 bits | ✅ | WIP | WIP | WIP | WIP | | Q5_K | 5 bits | ✅ | WIP | WIP | WIP | WIP | | Q4_0 | 4 bits | ✅ | ✅ | WIP | WIP | WIP | | Q4_1 | 4 bits | ✅ | ✅ | ✅ | WIP | WIP | | Q4_K | 4 bits | ✅ | WIP | WIP | WIP | WIP | | Q3_K | 3 bits | ✅ | WIP | WIP | WIP | WIP | | Q2_K | 2 bits | ✅ | WIP | WIP | WIP | WIP | As the table above suggests, WebGPU-accelerated quantizations are still under busy development, and `Q8_0`， `Q4_0`， `Q4_1` are currently the most recommended quantization methods on CPUs! ## Usage ### Building the Project To build `crabml`, set the `RUSTFLAGS` environment variable to enable specific target features. For example, to enable NEON on ARM architectures, use `RUSTFLAGS="-C target-feature=+neon"`. Then build the project with the following command: ```bash cargo build --release ``` This command compiles the project in release mode, which optimizes the binary for performance. ### Running an Example After building the project, you can run an example inference by executing the `crabml-cli` binary with appropriate arguments. For instance, to use the `tinyllamas-stories-15m-f32.gguf` model to generate text based on the prompt "captain america", execute the command below: ```bash ./target/release/crabml-cli \ -m ./testdata/tinyllamas-stories-15m-f32.gguf \ "captain america" --steps 100 \ -t 0.8 -p 1.0 ``` In this command: - `-m` specifies the checkpoint file. - `--steps` defines the number of tokens to generate. - `-t` sets the temperature, which controls the randomness of the output. - `-p` sets the probability of sampling from the top-p. ## License This contribution is licensed under Apache License, Version 2.0, ([LICENSE](LICENSE) or <http://www.apache.org/licenses/LICENSE-2.0>) ", Assign "at most 3 tags" to the expected json: {"id":"8248","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"