diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml index 29adf56f3..ac9af6411 100644 --- a/.github/workflows/test.yaml +++ b/.github/workflows/test.yaml @@ -73,12 +73,12 @@ jobs: $env:CMAKE_SYSTEM_VERSION="10.0.22621.0" $env:PATH="$gopath;$gccpath;$env:PATH" echo $env:PATH - go generate -x ./... + $env:GOARCH=""; $env:OLLAMA_BUILD_TARGET_ARCH="${{ matrix.arch }}"; go generate -x ./... if: ${{ startsWith(matrix.os, 'windows-') }} - name: 'Windows Go Generate' - - run: go generate -x ./... + name: 'Windows Generate' + - run: GOARCH= OLLAMA_BUILD_TARGET_ARCH=${{ matrix.arch }} go generate -x ./... if: ${{ ! startsWith(matrix.os, 'windows-') }} - name: 'Unix Go Generate' + name: 'Unix Generate' - uses: actions/upload-artifact@v4 with: name: ${{ matrix.os }}-${{ matrix.arch }}-libraries @@ -184,7 +184,7 @@ jobs: $env:OLLAMA_SKIP_CPU_GENERATE="1" $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) go generate -x ./... - name: go generate + name: go generate -x ./... env: OLLAMA_SKIP_CPU_GENERATE: '1' # TODO - do we need any artifacts? @@ -217,7 +217,7 @@ jobs: - name: 'Verify CUDA' run: nvcc -V - run: go get ./... - - name: go generate + - name: go generate -x ./... run: | $gopath=(get-command go).source | split-path -parent $cudabin=(get-command nvcc).source | split-path @@ -312,7 +312,10 @@ jobs: touch llm/build/darwin/$ARCH/stub/bin/ollama_llama_server if: ${{ startsWith(matrix.os, 'macos-') }} shell: bash - - run: go generate ./... + - run: $env:GOARCH=""; $env:OLLAMA_BUILD_TARGET_ARCH="${{ matrix.arch }}"; go generate -x ./... + if: ${{ startsWith(matrix.os, 'windows-') }} + - run: GOARCH= OLLAMA_BUILD_TARGET_ARCH=${{ matrix.arch }} go generate -x ./... + if: ${{ ! startsWith(matrix.os, 'windows-') }} - run: go build - run: go test -v ./... - uses: actions/upload-artifact@v4 diff --git a/README.md b/README.md index 62f5cd65c..4bbf38556 100644 --- a/README.md +++ b/README.md @@ -1,12 +1,12 @@
- ollama + ollama
# Ollama [![Discord](https://dcbadge.vercel.app/api/server/ollama?style=flat&compact=true)](https://discord.gg/ollama) -Get up and running with large language models. +Get up and running with large language models locally. ### macOS @@ -51,17 +51,15 @@ Here are some example models that can be downloaded: | ------------------ | ---------- | ----- | ------------------------------ | | Llama 3 | 8B | 4.7GB | `ollama run llama3` | | Llama 3 | 70B | 40GB | `ollama run llama3:70b` | -| Phi 3 Mini | 3.8B | 2.3GB | `ollama run phi3` | -| Phi 3 Medium | 14B | 7.9GB | `ollama run phi3:medium` | -| Gemma 2 | 9B | 5.5GB | `ollama run gemma2` | -| Gemma 2 | 27B | 16GB | `ollama run gemma2:27b` | +| Phi-3 | 3,8B | 2.3GB | `ollama run phi3` | | Mistral | 7B | 4.1GB | `ollama run mistral` | -| Moondream 2 | 1.4B | 829MB | `ollama run moondream` | | Neural Chat | 7B | 4.1GB | `ollama run neural-chat` | | Starling | 7B | 4.1GB | `ollama run starling-lm` | | Code Llama | 7B | 3.8GB | `ollama run codellama` | | Llama 2 Uncensored | 7B | 3.8GB | `ollama run llama2-uncensored` | | LLaVA | 7B | 4.5GB | `ollama run llava` | +| Gemma | 2B | 1.4GB | `ollama run gemma:2b` | +| Gemma | 7B | 4.8GB | `ollama run gemma:7b` | | Solar | 10.7B | 6.1GB | `ollama run solar` | > Note: You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models. @@ -175,19 +173,13 @@ I'm a basic program that prints the famous "Hello, world!" message to the consol The image features a yellow smiley face, which is likely the central focus of the picture. ``` -### Pass the prompt as an argument +### Pass in prompt as arguments ``` $ ollama run llama3 "Summarize this file: $(cat README.md)" Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications. ``` -### Show model information - -``` -ollama show llama3 -``` - ### List models on your computer ``` @@ -200,7 +192,19 @@ ollama list ## Building -See the [developer guide](https://github.com/ollama/ollama/blob/main/docs/development.md) +Install `cmake` and `go`: + +``` +brew install cmake go +``` + +Then build the binary: + +``` +go run build.go +``` + +More detailed instructions can be found in the [developer guide](https://github.com/ollama/ollama/blob/main/docs/development.md) ### Running local builds @@ -248,7 +252,6 @@ See the [API documentation](./docs/api.md) for all endpoints. - [Open WebUI](https://github.com/open-webui/open-webui) - [Enchanted (macOS native)](https://github.com/AugustDev/enchanted) -- [Hollama](https://github.com/fmaclen/hollama) - [Lollms-Webui](https://github.com/ParisNeo/lollms-webui) - [LibreChat](https://github.com/danny-avila/LibreChat) - [Bionic GPT](https://github.com/bionic-gpt/bionic-gpt) @@ -275,24 +278,17 @@ See the [API documentation](./docs/api.md) for all endpoints. - [OllamaGUI](https://github.com/enoch1118/ollamaGUI) - [OpenAOE](https://github.com/InternLM/OpenAOE) - [Odin Runes](https://github.com/leonid20000/OdinRunes) -- [LLM-X](https://github.com/mrdjohnson/llm-x) (Progressive Web App) +- [LLM-X: Progressive Web App](https://github.com/mrdjohnson/llm-x) - [AnythingLLM (Docker + MacOs/Windows/Linux native app)](https://github.com/Mintplex-Labs/anything-llm) - [Ollama Basic Chat: Uses HyperDiv Reactive UI](https://github.com/rapidarchitect/ollama_basic_chat) - [Ollama-chats RPG](https://github.com/drazdra/ollama-chats) -- [QA-Pilot](https://github.com/reid41/QA-Pilot) (Chat with Code Repository) -- [ChatOllama](https://github.com/sugarforever/chat-ollama) (Open Source Chatbot based on Ollama with Knowledge Bases) -- [CRAG Ollama Chat](https://github.com/Nagi-ovo/CRAG-Ollama-Chat) (Simple Web Search with Corrective RAG) -- [RAGFlow](https://github.com/infiniflow/ragflow) (Open-source Retrieval-Augmented Generation engine based on deep document understanding) -- [StreamDeploy](https://github.com/StreamDeploy-DevRel/streamdeploy-llm-app-scaffold) (LLM Application Scaffold) -- [chat](https://github.com/swuecho/chat) (chat web app for teams) +- [QA-Pilot: Chat with Code Repository](https://github.com/reid41/QA-Pilot) +- [ChatOllama: Open Source Chatbot based on Ollama with Knowledge Bases](https://github.com/sugarforever/chat-ollama) +- [CRAG Ollama Chat: Simple Web Search with Corrective RAG](https://github.com/Nagi-ovo/CRAG-Ollama-Chat) +- [RAGFlow: Open-source Retrieval-Augmented Generation engine based on deep document understanding](https://github.com/infiniflow/ragflow) +- [chat: chat web app for teams](https://github.com/swuecho/chat) - [Lobe Chat](https://github.com/lobehub/lobe-chat) with [Integrating Doc](https://lobehub.com/docs/self-hosting/examples/ollama) -- [Ollama RAG Chatbot](https://github.com/datvodinh/rag-chatbot.git) (Local Chat with multiple PDFs using Ollama and RAG) -- [BrainSoup](https://www.nurgo-software.com/products/brainsoup) (Flexible native client with RAG & multi-agent automation) -- [macai](https://github.com/Renset/macai) (macOS client for Ollama, ChatGPT, and other compatible API back-ends) -- [Olpaka](https://github.com/Otacon/olpaka) (User-friendly Flutter Web App for Ollama) -- [OllamaSpring](https://github.com/CrazyNeil/OllamaSpring) (Ollama Client for macOS) -- [LLocal.in](https://github.com/kartikm7/llocal) (Easy to use Electron Desktop Client for Ollama) -- [Ollama with Google Mesop](https://github.com/rapidarchitect/ollama_mesop/) (Mesop Chat Client implementation with Ollama) +- [Ollama RAG Chatbot: Local Chat with multiples PDFs using Ollama and RAG.](https://github.com/datvodinh/rag-chatbot.git) ### Terminal @@ -315,7 +311,6 @@ See the [API documentation](./docs/api.md) for all endpoints. - [ShellOracle](https://github.com/djcopley/ShellOracle) - [tlm](https://github.com/yusufcanb/tlm) - [podman-ollama](https://github.com/ericcurtin/podman-ollama) -- [gollama](https://github.com/sammcj/gollama) ### Database @@ -326,20 +321,17 @@ See the [API documentation](./docs/api.md) for all endpoints. - [Pacman](https://archlinux.org/packages/extra/x86_64/ollama/) - [Helm Chart](https://artifacthub.io/packages/helm/ollama-helm/ollama) -- [Guix channel](https://codeberg.org/tusharhero/ollama-guix) ### Libraries - [LangChain](https://python.langchain.com/docs/integrations/llms/ollama) and [LangChain.js](https://js.langchain.com/docs/modules/model_io/models/llms/integrations/ollama) with [example](https://js.langchain.com/docs/use_cases/question_answering/local_retrieval_qa) - [LangChainGo](https://github.com/tmc/langchaingo/) with [example](https://github.com/tmc/langchaingo/tree/main/examples/ollama-completion-example) - [LangChain4j](https://github.com/langchain4j/langchain4j) with [example](https://github.com/langchain4j/langchain4j-examples/tree/main/ollama-examples/src/main/java) -- [LangChainRust](https://github.com/Abraxas-365/langchain-rust) with [example](https://github.com/Abraxas-365/langchain-rust/blob/main/examples/llm_ollama.rs) - [LlamaIndex](https://gpt-index.readthedocs.io/en/stable/examples/llm/ollama.html) - [LiteLLM](https://github.com/BerriAI/litellm) - [OllamaSharp for .NET](https://github.com/awaescher/OllamaSharp) - [Ollama for Ruby](https://github.com/gbaptista/ollama-ai) - [Ollama-rs for Rust](https://github.com/pepperoni21/ollama-rs) -- [Ollama-hpp for C++](https://github.com/jmont-dev/ollama-hpp) - [Ollama4j for Java](https://github.com/amithkoujalgi/ollama4j) - [ModelFusion Typescript Library](https://modelfusion.dev/integration/model-provider/ollama) - [OllamaKit for Swift](https://github.com/kevinhermawan/OllamaKit) @@ -350,13 +342,9 @@ See the [API documentation](./docs/api.md) for all endpoints. - [Haystack](https://github.com/deepset-ai/haystack-integrations/blob/main/integrations/ollama.md) - [Elixir LangChain](https://github.com/brainlid/langchain) - [Ollama for R - rollama](https://github.com/JBGruber/rollama) -- [Ollama for R - ollama-r](https://github.com/hauselin/ollama-r) - [Ollama-ex for Elixir](https://github.com/lebrunel/ollama-ex) - [Ollama Connector for SAP ABAP](https://github.com/b-tocs/abap_btocs_ollama) - [Testcontainers](https://testcontainers.com/modules/ollama/) -- [Portkey](https://portkey.ai/docs/welcome/integration-guides/ollama) -- [PromptingTools.jl](https://github.com/svilupp/PromptingTools.jl) with an [example](https://svilupp.github.io/PromptingTools.jl/dev/examples/working_with_ollama) -- [LlamaScript](https://github.com/Project-Llama/llamascript) ### Mobile @@ -376,23 +364,18 @@ See the [API documentation](./docs/api.md) for all endpoints. - [Ollama Telegram Bot](https://github.com/ruecat/ollama-telegram) - [Hass Ollama Conversation](https://github.com/ej52/hass-ollama-conversation) - [Rivet plugin](https://github.com/abrenneke/rivet-plugin-ollama) +- [Llama Coder](https://github.com/ex3ndr/llama-coder) (Copilot alternative using Ollama) - [Obsidian BMO Chatbot plugin](https://github.com/longy2k/obsidian-bmo-chatbot) - [Cliobot](https://github.com/herval/cliobot) (Telegram bot with Ollama support) - [Copilot for Obsidian plugin](https://github.com/logancyang/obsidian-copilot) - [Obsidian Local GPT plugin](https://github.com/pfrankov/obsidian-local-gpt) - [Open Interpreter](https://docs.openinterpreter.com/language-model-setup/local-models/ollama) -- [Llama Coder](https://github.com/ex3ndr/llama-coder) (Copilot alternative using Ollama) -- [Ollama Copilot](https://github.com/bernardo-bruning/ollama-copilot) (Proxy that allows you to use ollama as a copilot like Github copilot) - [twinny](https://github.com/rjmacarthy/twinny) (Copilot and Copilot chat alternative using Ollama) - [Wingman-AI](https://github.com/RussellCanfield/wingman-ai) (Copilot code and chat alternative using Ollama and HuggingFace) - [Page Assist](https://github.com/n4ze3m/page-assist) (Chrome Extension) - [AI Telegram Bot](https://github.com/tusharhero/aitelegrambot) (Telegram bot using Ollama in backend) - [AI ST Completion](https://github.com/yaroslavyaroslav/OpenAI-sublime-text) (Sublime Text 4 AI assistant plugin with Ollama support) - [Discord-Ollama Chat Bot](https://github.com/kevinthedang/discord-ollama) (Generalized TypeScript Discord Bot w/ Tuning Documentation) -- [Discord AI chat/moderation bot](https://github.com/rapmd73/Companion) Chat/moderation bot written in python. Uses Ollama to create personalities. -- [Headless Ollama](https://github.com/nischalj10/headless-ollama) (Scripts to automatically install ollama client & models on any OS for apps that depends on ollama server) - -### Supported backends - -- [llama.cpp](https://github.com/ggerganov/llama.cpp) project founded by Georgi Gerganov. +### Supported backends +- [llama.cpp](https://github.com/ggerganov/llama.cpp) project founded by Georgi Gerganov. diff --git a/build.go b/build.go new file mode 100644 index 000000000..e6446d2a3 --- /dev/null +++ b/build.go @@ -0,0 +1,199 @@ +//go:build ignore + +package main + +import ( + "cmp" + "errors" + "flag" + "log" + "os" + "os/exec" + "path/filepath" + "runtime" +) + +// Flags +var ( + flagRegenerateDestroy = flag.Bool("d", false, "force regenerate the dependencies (destructive)") + flagRegenerateGently = flag.Bool("g", false, "regenerate the dependencies (non-destructive)") + flagSkipBuild = flag.Bool("s", false, "generate dependencies only (e.g. skip 'go build .')") + + // Flags to set GOARCH explicitly for cross-platform builds, + // e.g., in CI to target a different platform than the build matrix + // default. These allows us to run generate without a separate build + // step for building the script binary for the host ARCH and then + // runing the generate script for the target ARCH. Instead, we can + // just run `go run build.go -target=$GOARCH` to generate the + // deps. + flagGOARCH = flag.String("target", "", "sets GOARCH to use when generating dependencies and building") +) + +func buildEnv() []string { + return append(os.Environ(), "GOARCH="+cmp.Or( + *flagGOARCH, + os.Getenv("OLLAMA_BUILD_TARGET_ARCH"), + runtime.GOARCH, + )) +} + +func main() { + log.SetFlags(0) + flag.Usage = func() { + log.Printf("Usage: go run build.go [flags]") + log.Println() + log.Println("Flags:") + flag.PrintDefaults() + log.Println() + log.Println("This script builds the Ollama server binary and generates the llama.cpp") + log.Println("bindings for the current platform. It assumes that the current working") + log.Println("directory is the root directory of the Ollama project.") + log.Println() + log.Println("If the -d flag is provided, the script will force regeneration of the") + log.Println("dependencies; removing the 'llm/build' directory before starting.") + log.Println() + log.Println("If the -g flag is provided, the script will regenerate the dependencies") + log.Println("without removing the 'llm/build' directory.") + log.Println() + log.Println("If the -s flag is provided, the script will skip building the Ollama binary") + log.Println() + log.Println("If the -target flag is provided, the script will set GOARCH to the value") + log.Println("of the flag. This is useful for cross-platform builds.") + log.Println() + log.Println("The script will check for the required dependencies (cmake, gcc) and") + log.Println("print their version.") + log.Println() + log.Println("The script will also check if it is being run from the root directory of") + log.Println("the Ollama project.") + log.Println() + os.Exit(1) + } + flag.Parse() + + log.Printf("=== Building Ollama ===") + defer func() { + log.Printf("=== Done building Ollama ===") + if !*flagSkipBuild { + log.Println() + log.Println("To run the Ollama server, use:") + log.Println() + log.Println(" ./ollama serve") + log.Println() + } + }() + + if flag.NArg() > 0 { + flag.Usage() + } + + if !inRootDir() { + log.Fatalf("Please run this script from the root directory of the Ollama project.") + } + + if err := checkDependencies(); err != nil { + log.Fatalf("Failed dependency check: %v", err) + } + if err := buildLlammaCPP(); err != nil { + log.Fatalf("Failed to build llama.cpp: %v", err) + } + if err := goBuildOllama(); err != nil { + log.Fatalf("Failed to build ollama Go binary: %v", err) + } +} + +// checkDependencies does a quick check to see if the required dependencies are +// installed on the system and functioning enough to print their version. +// +// TODO(bmizerany): Check the actual version of the dependencies? Seems a +// little daunting given diff versions might print diff things. This should +// be good enough for now. +func checkDependencies() error { + var err error + check := func(name string, args ...string) { + log.Printf("=== Checking for %s ===", name) + defer log.Printf("=== Done checking for %s ===\n\n", name) + cmd := exec.Command(name, args...) + cmd.Stdout = os.Stdout + cmd.Stderr = os.Stderr + err = errors.Join(err, cmd.Run()) + } + + check("cmake", "--version") + check("gcc", "--version") + return err +} + +func goBuildOllama() error { + log.Println("=== Building Ollama binary ===") + defer log.Printf("=== Done building Ollama binary ===\n\n") + if *flagSkipBuild { + log.Println("Skipping 'go build -o ollama .'") + return nil + } + cmd := exec.Command("go", "build", "-o", "ollama", ".") + cmd.Stdout = os.Stdout + cmd.Stderr = os.Stderr + cmd.Env = buildEnv() + return cmd.Run() +} + +// buildLlammaCPP generates the llama.cpp bindings for the current platform. +// +// It assumes that the current working directory is the root directory of the +// Ollama project. +func buildLlammaCPP() error { + log.Println("=== Generating dependencies ===") + defer log.Printf("=== Done generating dependencies ===\n\n") + if *flagRegenerateDestroy { + if err := os.RemoveAll(filepath.Join("llm", "build")); err != nil { + return err + } + } + if isDirectory(filepath.Join("llm", "build")) && !*flagRegenerateGently { + log.Println("llm/build already exists; skipping. Use -d or -g to re-generate.") + return nil + } + + scriptDir, err := filepath.Abs(filepath.Join("llm", "generate")) + if err != nil { + return err + } + + var cmd *exec.Cmd + switch runtime.GOOS { + case "windows": + script := filepath.Join(scriptDir, "gen_windows.ps1") + cmd = exec.Command("powershell", "-ExecutionPolicy", "Bypass", "-File", script) + case "linux": + script := filepath.Join(scriptDir, "gen_linux.sh") + cmd = exec.Command("bash", script) + case "darwin": + script := filepath.Join(scriptDir, "gen_darwin.sh") + cmd = exec.Command("bash", script) + default: + log.Fatalf("Unsupported OS: %s", runtime.GOOS) + } + cmd.Dir = filepath.Join("llm", "generate") + cmd.Stdout = os.Stdout + cmd.Stderr = os.Stderr + cmd.Env = buildEnv() + + log.Printf("Running GOOS=%s GOARCH=%s %s", runtime.GOOS, runtime.GOARCH, cmd.Args) + + return cmd.Run() +} + +func isDirectory(path string) bool { + info, err := os.Stat(path) + if err != nil { + return false + } + return info.IsDir() +} + +// inRootDir returns true if the current working directory is the root +// directory of the Ollama project. It looks for a file named "go.mod". +func inRootDir() bool { + _, err := os.Stat("go.mod") + return err == nil +} diff --git a/docs/development.md b/docs/development.md index 2a6886a43..1f54e0320 100644 --- a/docs/development.md +++ b/docs/development.md @@ -25,13 +25,7 @@ export OLLAMA_DEBUG=1 Get the required libraries and build the native LLM code: ```bash -go generate ./... -``` - -Then build ollama: - -```bash -go build . +go run build.go ``` Now you can run `ollama`: @@ -40,6 +34,16 @@ Now you can run `ollama`: ./ollama ``` +### Rebuilding the native code + +If at any point you need to rebuild the native code, you can run the +build.go script again using the `-f` flag to force a rebuild, and, +optionally, the `-d` flag to skip building the Go binary: + +```bash +go run build.go -d -s +``` + ### Linux #### Linux CUDA (NVIDIA) @@ -55,16 +59,10 @@ specifying an environment variable `CUDA_LIB_DIR` to the location of the shared libraries, and `CUDACXX` to the location of the nvcc compiler. You can customize a set of target CUDA architectures by setting `CMAKE_CUDA_ARCHITECTURES` (e.g. "50;60;70") -Then generate dependencies: - -``` -go generate ./... -``` - Then build the binary: ``` -go build . +go run build.go ``` #### Linux ROCm (AMD) @@ -80,21 +78,17 @@ install (typically `/opt/rocm`), and `CLBlast_DIR` to the location of the CLBlast install (typically `/usr/lib/cmake/CLBlast`). You can also customize the AMD GPU targets by setting AMDGPU_TARGETS (e.g. `AMDGPU_TARGETS="gfx1101;gfx1102"`) -``` -go generate ./... -``` - Then build the binary: ``` -go build . +go run build.go ``` ROCm requires elevated privileges to access the GPU at runtime. On most distros you can add your user account to the `render` group, or run as root. #### Advanced CPU Settings -By default, running `go generate ./...` will compile a few different variations +By default, running `go run build.go` will compile a few different variations of the LLM library based on common CPU families and vector math capabilities, including a lowest-common-denominator which should run on almost any 64 bit CPU somewhat slowly. At runtime, Ollama will auto-detect the optimal variation to @@ -104,8 +98,7 @@ like to use. For example, to compile an optimized binary for an Intel i9-9880H, you might use: ``` -OLLAMA_CUSTOM_CPU_DEFS="-DLLAMA_AVX=on -DLLAMA_AVX2=on -DLLAMA_F16C=on -DLLAMA_FMA=on" go generate ./... -go build . +OLLAMA_CUSTOM_CPU_DEFS="-DLLAMA_AVX=on -DLLAMA_AVX2=on -DLLAMA_F16C=on -DLLAMA_FMA=on" go run build.go ``` #### Containerized Linux Build @@ -129,8 +122,7 @@ Then, build the `ollama` binary: ```powershell $env:CGO_ENABLED="1" -go generate ./... -go build . +go run build.go ``` #### Windows CUDA (NVIDIA) diff --git a/llm/generate/gen_darwin.sh b/llm/generate/gen_darwin.sh index 721a9ae80..7a019942a 100755 --- a/llm/generate/gen_darwin.sh +++ b/llm/generate/gen_darwin.sh @@ -1,6 +1,6 @@ #!/bin/bash -# This script is intended to run inside the go generate -# working directory must be ./llm/generate/ +# This script is intended to run inside the `go run build.go` script, which +# sets the working directory to the correct location: ./llm/generate/. # TODO - add hardening to detect missing tools (cmake, etc.) @@ -92,10 +92,10 @@ case "${GOARCH}" in ;; *) echo "GOARCH must be set" - echo "this script is meant to be run from within go generate" + echo "this script is meant to be run from within 'go run build.go'" exit 1 ;; esac cleanup -echo "go generate completed. LLM runners: $(cd ${BUILD_DIR}/..; echo *)" +echo "code generation completed. LLM runners: $(cd ${BUILD_DIR}/..; echo *)" diff --git a/llm/generate/gen_linux.sh b/llm/generate/gen_linux.sh index 28ce1f21d..b2cd76a6f 100755 --- a/llm/generate/gen_linux.sh +++ b/llm/generate/gen_linux.sh @@ -1,6 +1,6 @@ #!/bin/bash -# This script is intended to run inside the go generate -# working directory must be llm/generate/ +# This script is intended to run with the `go run build.go` script, which +# sets the working directory to the correct location: ./llm/generate/. # First we build one or more CPU based LLM libraries # @@ -281,4 +281,4 @@ if [ -z "${OLLAMA_SKIP_ROCM_GENERATE}" -a -d "${ROCM_PATH}" ]; then fi cleanup -echo "go generate completed. LLM runners: $(cd ${BUILD_DIR}/..; echo *)" +echo "code generation completed. LLM runners: $(cd ${BUILD_DIR}/..; echo *)" diff --git a/llm/generate/gen_windows.ps1 b/llm/generate/gen_windows.ps1 index e217a0382..8c07ad065 100644 --- a/llm/generate/gen_windows.ps1 +++ b/llm/generate/gen_windows.ps1 @@ -26,26 +26,15 @@ function amdGPUs { $GPU_LIST -join ';' } - function init_vars { - if (!$script:SRC_DIR) { - $script:SRC_DIR = $(resolve-path "..\..\") - } - if (!$script:llamacppDir) { - $script:llamacppDir = "../llama.cpp" - } - if (!$script:cmakeTargets) { - $script:cmakeTargets = @("ollama_llama_server") - } + $script:SRC_DIR = $(resolve-path "..\..\") + $script:llamacppDir = "../llama.cpp" $script:cmakeDefs = @( "-DBUILD_SHARED_LIBS=on", - "-DLLAMA_NATIVE=off", - "-DLLAMA_OPENMP=off" + "-DLLAMA_NATIVE=off" ) - $script:commonCpuDefs = @("-DCMAKE_POSITION_INDEPENDENT_CODE=on") - $script:ARCH = $Env:PROCESSOR_ARCHITECTURE.ToLower() - $script:DIST_BASE = "${script:SRC_DIR}\dist\windows-${script:ARCH}\ollama_runners" - md "$script:DIST_BASE" -ea 0 > $null + $script:cmakeTargets = @("ollama_llama_server") + $script:ARCH = "amd64" # arm not yet supported. if ($env:CGO_CFLAGS -contains "-g") { $script:cmakeDefs += @("-DCMAKE_VERBOSE_MAKEFILE=on", "-DLLAMA_SERVER_VERBOSE=on", "-DCMAKE_BUILD_TYPE=RelWithDebInfo") $script:config = "RelWithDebInfo" @@ -66,6 +55,7 @@ function init_vars { } else { $script:CUDA_LIB_DIR=$env:CUDA_LIB_DIR } + $script:GZIP=(get-command -ea 'silentlycontinue' gzip).path $script:DUMPBIN=(get-command -ea 'silentlycontinue' dumpbin).path if ($null -eq $env:CMAKE_CUDA_ARCHITECTURES) { $script:CMAKE_CUDA_ARCHITECTURES="50;52;61;70;75;80" @@ -123,13 +113,8 @@ function build { & cmake --version & cmake -S "${script:llamacppDir}" -B $script:buildDir $script:cmakeDefs if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)} - if ($cmakeDefs -contains "-G") { - $extra=@("-j8") - } else { - $extra= @("--", "/p:CL_MPcount=8") - } - write-host "building with: cmake --build $script:buildDir --config $script:config $($script:cmakeTargets | ForEach-Object { `"--target`", $_ }) $extra" - & cmake --build $script:buildDir --config $script:config ($script:cmakeTargets | ForEach-Object { "--target", $_ }) $extra + write-host "building with: cmake --build $script:buildDir --config $script:config $($script:cmakeTargets | ForEach-Object { `"--target`", $_ })" + & cmake --build $script:buildDir --config $script:config ($script:cmakeTargets | ForEach-Object { "--target", $_ }) if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)} # Rearrange output to be consistent between different generators if ($null -ne ${script:config} -And (test-path -path "${script:buildDir}/bin/${script:config}" ) ) { @@ -149,18 +134,21 @@ function sign { } } -function install { - write-host "Installing binaries to dist dir ${script:distDir}" - mkdir ${script:distDir} -ErrorAction SilentlyContinue +function compress { + if ($script:GZIP -eq $null) { + write-host "gzip not installed, not compressing files" + return + } + write-host "Compressing binaries..." $binaries = dir "${script:buildDir}/bin/*.exe" foreach ($file in $binaries) { - copy-item -Path $file -Destination ${script:distDir} -Force + & "$script:GZIP" --best -f $file } - write-host "Installing dlls to dist dir ${script:distDir}" + write-host "Compressing dlls..." $dlls = dir "${script:buildDir}/bin/*.dll" foreach ($file in $dlls) { - copy-item -Path $file -Destination ${script:distDir} -Force + & "$script:GZIP" --best -f $file } } @@ -181,252 +169,132 @@ function cleanup { } } +init_vars +git_module_setup +apply_patches # -DLLAMA_AVX -- 2011 Intel Sandy Bridge & AMD Bulldozer # -DLLAMA_AVX2 -- 2013 Intel Haswell & 2015 AMD Excavator / 2017 AMD Zen # -DLLAMA_FMA (FMA3) -- 2013 Intel Haswell & 2012 AMD Piledriver +$script:commonCpuDefs = @("-DCMAKE_POSITION_INDEPENDENT_CODE=on") -function build_static() { - if ((-not "${env:OLLAMA_SKIP_STATIC_GENERATE}") -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "static"))) { - # GCC build for direct linking into the Go binary - init_vars - # cmake will silently fallback to msvc compilers if mingw isn't in the path, so detect and fail fast - # as we need this to be compiled by gcc for golang to be able to link with itx - write-host "Checking for MinGW..." - # error action ensures we exit on failure - get-command gcc - get-command mingw32-make - $oldTargets = $script:cmakeTargets - $script:cmakeTargets = @("llama", "ggml") - $script:cmakeDefs = @( - "-G", "MinGW Makefiles" - "-DCMAKE_C_COMPILER=gcc.exe", - "-DCMAKE_CXX_COMPILER=g++.exe", - "-DBUILD_SHARED_LIBS=off", - "-DLLAMA_NATIVE=off", - "-DLLAMA_AVX=off", - "-DLLAMA_AVX2=off", - "-DLLAMA_AVX512=off", - "-DLLAMA_F16C=off", - "-DLLAMA_FMA=off", - "-DLLAMA_OPENMP=off") - $script:buildDir="../build/windows/${script:ARCH}_static" - write-host "Building static library" - build - $script:cmakeTargets = $oldTargets - } else { - write-host "Skipping CPU generation step as requested" - } +if ($null -eq ${env:OLLAMA_SKIP_CPU_GENERATE}) { + +# GCC build for direct linking into the Go binary +init_vars +# cmake will silently fallback to msvc compilers if mingw isn't in the path, so detect and fail fast +# as we need this to be compiled by gcc for golang to be able to link with itx +write-host "Checking for MinGW..." +# error action ensures we exit on failure +get-command gcc +get-command mingw32-make +$script:cmakeTargets = @("llama", "ggml") +$script:cmakeDefs = @( + "-G", "MinGW Makefiles" + "-DCMAKE_C_COMPILER=gcc.exe", + "-DCMAKE_CXX_COMPILER=g++.exe", + "-DBUILD_SHARED_LIBS=off", + "-DLLAMA_NATIVE=off", + "-DLLAMA_AVX=off", + "-DLLAMA_AVX2=off", + "-DLLAMA_AVX512=off", + "-DLLAMA_F16C=off", + "-DLLAMA_FMA=off") +$script:buildDir="../build/windows/${script:ARCH}_static" +write-host "Building static library" +build + +# remaining llama.cpp builds use MSVC + init_vars + $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DLLAMA_AVX=off", "-DLLAMA_AVX2=off", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=off", "-DLLAMA_F16C=off") + $script:cmakeDefs + $script:buildDir="../build/windows/${script:ARCH}/cpu" + write-host "Building LCD CPU" + build + sign + compress + + init_vars + $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DLLAMA_AVX=on", "-DLLAMA_AVX2=off", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=off", "-DLLAMA_F16C=off") + $script:cmakeDefs + $script:buildDir="../build/windows/${script:ARCH}/cpu_avx" + write-host "Building AVX CPU" + build + sign + compress + + init_vars + $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DLLAMA_AVX=on", "-DLLAMA_AVX2=on", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=on", "-DLLAMA_F16C=on") + $script:cmakeDefs + $script:buildDir="../build/windows/${script:ARCH}/cpu_avx2" + write-host "Building AVX2 CPU" + build + sign + compress +} else { + write-host "Skipping CPU generation step as requested" } -function build_cpu($gen_arch) { - if ((-not "${env:OLLAMA_SKIP_CPU_GENERATE}" ) -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "cpu"))) { - # remaining llama.cpp builds use MSVC - init_vars - $script:cmakeDefs = $script:commonCpuDefs + @("-A", $gen_arch, "-DLLAMA_AVX=off", "-DLLAMA_AVX2=off", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=off", "-DLLAMA_F16C=off") + $script:cmakeDefs - $script:buildDir="../build/windows/${script:ARCH}/cpu" - $script:distDir="$script:DIST_BASE\cpu" - write-host "Building LCD CPU" - build - sign - install - } else { - write-host "Skipping CPU generation step as requested" - } -} - -function build_cpu_avx() { - if ((-not "${env:OLLAMA_SKIP_CPU_GENERATE}" ) -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "cpu_avx"))) { - init_vars - $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DLLAMA_AVX=on", "-DLLAMA_AVX2=off", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=off", "-DLLAMA_F16C=off") + $script:cmakeDefs - $script:buildDir="../build/windows/${script:ARCH}/cpu_avx" - $script:distDir="$script:DIST_BASE\cpu_avx" - write-host "Building AVX CPU" - build - sign - install - } else { - write-host "Skipping CPU AVX generation step as requested" - } -} - -function build_cpu_avx2() { - if ((-not "${env:OLLAMA_SKIP_CPU_GENERATE}" ) -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "cpu_avx2"))) { - init_vars - $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DLLAMA_AVX=on", "-DLLAMA_AVX2=on", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=on", "-DLLAMA_F16C=on") + $script:cmakeDefs - $script:buildDir="../build/windows/${script:ARCH}/cpu_avx2" - $script:distDir="$script:DIST_BASE\cpu_avx2" - write-host "Building AVX2 CPU" - build - sign - install - } else { - write-host "Skipping CPU AVX2 generation step as requested" - } -} - -function build_cuda() { - if ((-not "${env:OLLAMA_SKIP_CUDA_GENERATE}") -and ("${script:CUDA_LIB_DIR}")) { - # Then build cuda as a dynamically loaded library - $nvcc = "$script:CUDA_LIB_DIR\nvcc.exe" - $script:CUDA_VERSION=(get-item ($nvcc | split-path | split-path)).Basename - if ($null -ne $script:CUDA_VERSION) { - $script:CUDA_VARIANT="_"+$script:CUDA_VERSION - } - init_vars - $script:buildDir="../build/windows/${script:ARCH}/cuda$script:CUDA_VARIANT" - $script:distDir="$script:DIST_BASE\cuda$script:CUDA_VARIANT" - $script:cmakeDefs += @( - "-A", "x64", - "-DLLAMA_CUDA=ON", - "-DLLAMA_AVX=on", - "-DLLAMA_AVX2=off", - "-DCUDAToolkit_INCLUDE_DIR=$script:CUDA_INCLUDE_DIR", - "-DCMAKE_CUDA_FLAGS=-t8", - "-DCMAKE_CUDA_ARCHITECTURES=${script:CMAKE_CUDA_ARCHITECTURES}" - ) - if ($null -ne $env:OLLAMA_CUSTOM_CUDA_DEFS) { - write-host "OLLAMA_CUSTOM_CUDA_DEFS=`"${env:OLLAMA_CUSTOM_CUDA_DEFS}`"" - $script:cmakeDefs +=@("${env:OLLAMA_CUSTOM_CUDA_DEFS}") - write-host "building custom CUDA GPU" - } - build - sign - install - - rm -ea 0 -recurse -force -path "${script:SRC_DIR}\dist\windows-${script:ARCH}\cuda\" - md "${script:SRC_DIR}\dist\windows-${script:ARCH}\cuda\" -ea 0 > $null - write-host "copying CUDA dependencies to ${script:SRC_DIR}\dist\windows-${script:ARCH}\cuda\" - cp "${script:CUDA_LIB_DIR}\cudart64_*.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\cuda\" - cp "${script:CUDA_LIB_DIR}\cublas64_*.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\cuda\" - cp "${script:CUDA_LIB_DIR}\cublasLt64_*.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\cuda\" - } else { - write-host "Skipping CUDA generation step" - } -} - -function build_oneapi() { - if ((-not "${env:OLLAMA_SKIP_ONEAPI_GENERATE}") -and ("${env:ONEAPI_ROOT}")) { - # Get oneAPI version - $script:ONEAPI_VERSION = icpx --version - $script:ONEAPI_VERSION = [regex]::Match($script:ONEAPI_VERSION, '(?<=oneAPI DPC\+\+/C\+\+ Compiler )(?\d+\.\d+\.\d+)').Value - if ($null -ne $script:ONEAPI_VERSION) { - $script:ONEAPI_VARIANT = "_v" + $script:ONEAPI_VERSION +if ($null -ne $script:CUDA_LIB_DIR) { + # Then build cuda as a dynamically loaded library + $nvcc = "$script:CUDA_LIB_DIR\nvcc.exe" + $script:CUDA_VERSION=(get-item ($nvcc | split-path | split-path)).Basename + if ($null -ne $script:CUDA_VERSION) { + $script:CUDA_VARIANT="_"+$script:CUDA_VERSION } init_vars - $script:buildDir = "../build/windows/${script:ARCH}/oneapi$script:ONEAPI_VARIANT" - $script:distDir ="$script:DIST_BASE\oneapi$script:ONEAPI_VARIANT" - $script:cmakeDefs += @( - "-G", "MinGW Makefiles", - "-DLLAMA_SYCL=ON", - "-DCMAKE_C_COMPILER=icx", - "-DCMAKE_CXX_COMPILER=icx", - "-DCMAKE_BUILD_TYPE=Release" - ) + $script:buildDir="../build/windows/${script:ARCH}/cuda$script:CUDA_VARIANT" + $script:cmakeDefs += @("-A", "x64", "-DLLAMA_CUDA=ON", "-DLLAMA_AVX=on", "-DLLAMA_AVX2=off", "-DCUDAToolkit_INCLUDE_DIR=$script:CUDA_INCLUDE_DIR", "-DCMAKE_CUDA_ARCHITECTURES=${script:CMAKE_CUDA_ARCHITECTURES}") + if ($null -ne $env:OLLAMA_CUSTOM_CUDA_DEFS) { + write-host "OLLAMA_CUSTOM_CUDA_DEFS=`"${env:OLLAMA_CUSTOM_CUDA_DEFS}`"" + $script:cmakeDefs +=@("${env:OLLAMA_CUSTOM_CUDA_DEFS}") + write-host "building custom CUDA GPU" + } + build + sign + compress +} - Write-Host "Building oneAPI" +if ($null -ne $env:HIP_PATH) { + $script:ROCM_VERSION=(get-item $env:HIP_PATH).Basename + if ($null -ne $script:ROCM_VERSION) { + $script:ROCM_VARIANT="_v"+$script:ROCM_VERSION + } + + init_vars + $script:buildDir="../build/windows/${script:ARCH}/rocm$script:ROCM_VARIANT" + $script:cmakeDefs += @( + "-G", "Ninja", + "-DCMAKE_C_COMPILER=clang.exe", + "-DCMAKE_CXX_COMPILER=clang++.exe", + "-DLLAMA_HIPBLAS=on", + "-DHIP_PLATFORM=amd", + "-DLLAMA_AVX=on", + "-DLLAMA_AVX2=off", + "-DCMAKE_POSITION_INDEPENDENT_CODE=on", + "-DAMDGPU_TARGETS=$(amdGPUs)", + "-DGPU_TARGETS=$(amdGPUs)" + ) + + # Make sure the ROCm binary dir is first in the path + $env:PATH="$env:HIP_PATH\bin;$env:PATH" + + # We have to clobber the LIB var from the developer shell for clang to work properly + $env:LIB="" + if ($null -ne $env:OLLAMA_CUSTOM_ROCM_DEFS) { + write-host "OLLAMA_CUSTOM_ROCM_DEFS=`"${env:OLLAMA_CUSTOM_ROCM_DEFS}`"" + $script:cmakeDefs += @("${env:OLLAMA_CUSTOM_ROCM_DEFS}") + write-host "building custom ROCM GPU" + } + write-host "Building ROCm" build # Ninja doesn't prefix with config name + ${script:config}="" if ($null -ne $script:DUMPBIN) { - & "$script:DUMPBIN" /dependents "${script:buildDir}/bin/ollama_llama_server.exe" | Select-String ".dll" + & "$script:DUMPBIN" /dependents "${script:buildDir}/bin/ollama_llama_server.exe" | select-string ".dll" } sign - install - - rm -ea 0 -recurse -force -path "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - md "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" -ea 0 > $null - cp "${env:ONEAPI_ROOT}\compiler\latest\bin\libirngmd.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\compiler\latest\bin\libmmd.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\compiler\latest\bin\pi_level_zero.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\compiler\latest\bin\pi_unified_runtime.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\compiler\latest\bin\pi_win_proxy_loader.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\compiler\latest\bin\svml_dispmd.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\compiler\latest\bin\sycl7.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\mkl\latest\bin\mkl_core.2.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\mkl\latest\bin\mkl_sycl_blas.4.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - cp "${env:ONEAPI_ROOT}\mkl\latest\bin\mkl_tbb_thread.2.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\oneapi\" - } else { - Write-Host "Skipping oneAPI generation step" - } + compress } -function build_rocm() { - if ((-not "${env:OLLAMA_SKIP_ROCM_GENERATE}") -and ("${env:HIP_PATH}")) { - $script:ROCM_VERSION=(get-item $env:HIP_PATH).Basename - if ($null -ne $script:ROCM_VERSION) { - $script:ROCM_VARIANT="_v"+$script:ROCM_VERSION - } - init_vars - $script:buildDir="../build/windows/${script:ARCH}/rocm$script:ROCM_VARIANT" - $script:distDir="$script:DIST_BASE\rocm$script:ROCM_VARIANT" - $script:cmakeDefs += @( - "-G", "Ninja", - "-DCMAKE_C_COMPILER=clang.exe", - "-DCMAKE_CXX_COMPILER=clang++.exe", - "-DLLAMA_HIPBLAS=on", - "-DHIP_PLATFORM=amd", - "-DLLAMA_AVX=on", - "-DLLAMA_AVX2=off", - "-DCMAKE_POSITION_INDEPENDENT_CODE=on", - "-DAMDGPU_TARGETS=$(amdGPUs)", - "-DGPU_TARGETS=$(amdGPUs)" - ) - - # Make sure the ROCm binary dir is first in the path - $env:PATH="$env:HIP_PATH\bin;$env:PATH" - - # We have to clobber the LIB var from the developer shell for clang to work properly - $env:LIB="" - if ($null -ne $env:OLLAMA_CUSTOM_ROCM_DEFS) { - write-host "OLLAMA_CUSTOM_ROCM_DEFS=`"${env:OLLAMA_CUSTOM_ROCM_DEFS}`"" - $script:cmakeDefs += @("${env:OLLAMA_CUSTOM_ROCM_DEFS}") - write-host "building custom ROCM GPU" - } - write-host "Building ROCm" - build - # Ninja doesn't prefix with config name - ${script:config}="" - if ($null -ne $script:DUMPBIN) { - & "$script:DUMPBIN" /dependents "${script:buildDir}/bin/ollama_llama_server.exe" | select-string ".dll" - } - sign - install - - # Assumes v5.7, may need adjustments for v6 - rm -ea 0 -recurse -force -path "${script:SRC_DIR}\dist\windows-${script:ARCH}\rocm\" - md "${script:SRC_DIR}\dist\windows-${script:ARCH}\rocm\rocblas\library\" -ea 0 > $null - cp "${env:HIP_PATH}\bin\hipblas.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\rocm\" - cp "${env:HIP_PATH}\bin\rocblas.dll" "${script:SRC_DIR}\dist\windows-${script:ARCH}\rocm\" - # amdhip64.dll dependency comes from the driver and must be installed on the host to use AMD GPUs - cp "${env:HIP_PATH}\bin\rocblas\library\*" "${script:SRC_DIR}\dist\windows-${script:ARCH}\rocm\rocblas\library\" - } else { - write-host "Skipping ROCm generation step" - } -} - -init_vars -if ($($args.count) -eq 0) { - git_module_setup - apply_patches - build_static - if ($script:ARCH -eq "arm64") { - build_cpu("ARM64") - } else { # amd64 - build_cpu("x64") - build_cpu_avx - build_cpu_avx2 - build_cuda - build_oneapi - build_rocm - } - - cleanup - write-host "`ngo generate completed. LLM runners: $(get-childitem -path $script:DIST_BASE)" -} else { - for ( $i = 0; $i -lt $args.count; $i++ ) { - write-host "performing $($args[$i])" - & $($args[$i]) - } -} \ No newline at end of file +cleanup +write-host "`code generation completed. LLM runners: $(get-childitem -path ${script:SRC_DIR}\llm\build\windows\${script:ARCH})" diff --git a/llm/generate/generate_darwin.go b/llm/generate/generate_darwin.go deleted file mode 100644 index 776852342..000000000 --- a/llm/generate/generate_darwin.go +++ /dev/null @@ -1,3 +0,0 @@ -package generate - -//go:generate bash ./gen_darwin.sh diff --git a/llm/generate/generate_linux.go b/llm/generate/generate_linux.go deleted file mode 100644 index 2b7e116db..000000000 --- a/llm/generate/generate_linux.go +++ /dev/null @@ -1,3 +0,0 @@ -package generate - -//go:generate bash ./gen_linux.sh diff --git a/llm/generate/generate_windows.go b/llm/generate/generate_windows.go deleted file mode 100644 index d2ee5428a..000000000 --- a/llm/generate/generate_windows.go +++ /dev/null @@ -1,3 +0,0 @@ -package generate - -//go:generate powershell -ExecutionPolicy Bypass -File ./gen_windows.ps1 diff --git a/main.go b/main.go index 158f0063c..4f7e26158 100644 --- a/main.go +++ b/main.go @@ -1,5 +1,7 @@ package main +//go:generate go run build.go -g -s + import ( "context"