Implement new Go based Desktop app

This focuses on Windows first, but coudl be used for Mac
and possibly linux in the future.

cmd/start_default.go

+//go:build !windows && !darwin
+
+package cmd
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/jmorganca/ollama/api"
+)
+
+func startApp(ctx context.Context, client *api.Client) error {
+	return fmt.Errorf("could not connect to ollama server, run 'ollama serve' to start it")
+}

cmd/start_windows.go

+package cmd
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"syscall"
+
+	"golang.org/x/sys/windows"
+
+	"github.com/jmorganca/ollama/api"
+)
+
+func init() {
+	var inMode uint32
+	var outMode uint32
+	var errMode uint32
+
+	in := windows.Handle(os.Stdin.Fd())
+	if err := windows.GetConsoleMode(in, &inMode); err == nil {
+		windows.SetConsoleMode(in, inMode|windows.ENABLE_VIRTUAL_TERMINAL_INPUT) //nolint:errcheck
+	}
+
+	out := windows.Handle(os.Stdout.Fd())
+	if err := windows.GetConsoleMode(out, &outMode); err == nil {
+		windows.SetConsoleMode(out, outMode|windows.ENABLE_VIRTUAL_TERMINAL_PROCESSING) //nolint:errcheck
+	}
+
+	errf := windows.Handle(os.Stderr.Fd())
+	if err := windows.GetConsoleMode(errf, &errMode); err == nil {
+		windows.SetConsoleMode(errf, errMode|windows.ENABLE_VIRTUAL_TERMINAL_PROCESSING) //nolint:errcheck
+	}
+}
+
+func startApp(ctx context.Context, client *api.Client) error {
+	// log.Printf("XXX Attempting to find and start ollama app")
+	AppName := "ollama app.exe"
+	exe, err := os.Executable()
+	if err != nil {
+		return err
+	}
+	appExe := filepath.Join(filepath.Dir(exe), AppName)
+	_, err = os.Stat(appExe)
+	if errors.Is(err, os.ErrNotExist) {
+		// Try the standard install location
+		localAppData := os.Getenv("LOCALAPPDATA")
+		appExe = filepath.Join(localAppData, "Ollama", AppName)
+		_, err := os.Stat(appExe)
+		if errors.Is(err, os.ErrNotExist) {
+			// Finally look in the path
+			appExe, err = exec.LookPath(AppName)
+			if err != nil {
+				return fmt.Errorf("could not locate ollama app")
+			}
+		}
+	}
+	// log.Printf("XXX attempting to start app %s", appExe)
+
+	cmd_path := "c:\\Windows\\system32\\cmd.exe"
+	cmd := exec.Command(cmd_path, "/c", appExe)
+	// TODO - these hide flags aren't working - still pops up a command window for some reason
+	cmd.SysProcAttr = &syscall.SysProcAttr{CreationFlags: 0x08000000, HideWindow: true}
+
+	// TODO this didn't help either...
+	cmd.Stdin = strings.NewReader("")
+	cmd.Stdout = os.Stdout
+	cmd.Stderr = os.Stderr
+
+	if err := cmd.Start(); err != nil {
+		return fmt.Errorf("unable to start ollama app %w", err)
+	}
+
+	if cmd.Process != nil {
+		defer cmd.Process.Release() //nolint:errcheck
+	}
+	return waitForServer(ctx, client)
+}

docs/troubleshooting.md

-# How to troubleshoot issues
-
-Sometimes Ollama may not perform as expected. One of the best ways to figure out what happened is to take a look at the logs. Find the logs on Mac by running the command:
-
-```shell
-cat ~/.ollama/logs/server.log
-```
-
-On Linux systems with systemd, the logs can be found with this command:
-
-```shell
-journalctl -u ollama
-```
-
-When you run Ollama in a container, the logs go to stdout/stderr in the container:
-
-```shell
-docker logs <container-name>
-```
-(Use `docker ps` to find the container name)
-
-If manually running `ollama serve` in a terminal, the logs will be on that terminal.
-
-Join the [Discord](https://discord.gg/ollama) for help interpreting the logs.
-
-## LLM libraries
-
-Ollama includes multiple LLM libraries compiled for different GPUs and CPU
-vector features.  Ollama tries to pick the best one based on the capabilities of
-your system.  If this autodetection has problems, or you run into other problems
-(e.g. crashes in your GPU) you can workaround this by forcing a specific LLM
-library.  `cpu_avx2` will perform the best, followed by `cpu_avx` an the slowest
-but most compatible is `cpu`.  Rosetta emulation under MacOS will work with the
-`cpu` library. 
-
-In the server log, you will see a message that looks something like this (varies
-from release to release):
-
-```
-Dynamic LLM libraries [rocm_v6 cpu cpu_avx cpu_avx2 cuda_v11 rocm_v5]
-```
-
-**Experimental LLM Library Override**
-
-You can set OLLAMA_LLM_LIBRARY to any of the available LLM libraries to bypass
-autodetection, so for example, if you have a CUDA card, but want to force the
-CPU LLM library with AVX2 vector support, use:
-
-```
-OLLAMA_LLM_LIBRARY="cpu_avx2" ollama serve
-```
-
-You can see what features your CPU has with the following.  
-```
-cat /proc/cpuinfo| grep flags  | head -1
-```
-
-## Known issues
-
+# How to troubleshoot issues
+
+Sometimes Ollama may not perform as expected. One of the best ways to figure out what happened is to take a look at the logs. Find the logs on **Mac** by running the command:
+
+```shell
+cat ~/.ollama/logs/server.log
+```
+
+On **Linux** systems with systemd, the logs can be found with this command:
+
+```shell
+journalctl -u ollama
+```
+
+When you run Ollama in a **container**, the logs go to stdout/stderr in the container:
+
+```shell
+docker logs <container-name>
+```
+(Use `docker ps` to find the container name)
+
+If manually running `ollama serve` in a terminal, the logs will be on that terminal.
+
+When you run Ollama on **Windows**, there are a few different locations.  You can view them in the explorer window by hitting `<cmd>+R` and type in:
+- `explorer %LOCALAPPDATA%\Ollama` to view logs
+- `explorer %LOCALAPPDATA%\Programs\Ollama` to browse the binaries (The installer adds this to your user PATH)
+- `explorer %HOMEPATH%\.ollama` to browse where models and configuration is stored
+- `explorer %TEMP%` where temporary executable files are stored in one or more `ollama*` directories
+
+To enable additional debug logging to help troubleshoot problems, first **Quit the running app from the tray menu** then in a powershell terminal
+```powershell
+$env:OLLAMA_DEBUG="1"
+& "ollama app.exe"
+```
+
+Join the [Discord](https://discord.gg/ollama) for help interpreting the logs.
+
+## LLM libraries
+
+Ollama includes multiple LLM libraries compiled for different GPUs and CPU
+vector features.  Ollama tries to pick the best one based on the capabilities of
+your system.  If this autodetection has problems, or you run into other problems
+(e.g. crashes in your GPU) you can workaround this by forcing a specific LLM
+library.  `cpu_avx2` will perform the best, followed by `cpu_avx` an the slowest
+but most compatible is `cpu`.  Rosetta emulation under MacOS will work with the
+`cpu` library. 
+
+In the server log, you will see a message that looks something like this (varies
+from release to release):
+
+```
+Dynamic LLM libraries [rocm_v6 cpu cpu_avx cpu_avx2 cuda_v11 rocm_v5]
+```
+
+**Experimental LLM Library Override**
+
+You can set OLLAMA_LLM_LIBRARY to any of the available LLM libraries to bypass
+autodetection, so for example, if you have a CUDA card, but want to force the
+CPU LLM library with AVX2 vector support, use:
+
+```
+OLLAMA_LLM_LIBRARY="cpu_avx2" ollama serve
+```
+
+You can see what features your CPU has with the following.  
+```
+cat /proc/cpuinfo| grep flags  | head -1
+```
+
+## Known issues
+
 * N/A
\ No newline at end of file

docs/windows.md

+# Ollama Windows Preview
+
+Welcome to the Ollama Windows preview.
+
+No more WSL required!
+
+Ollama now runs as a native Windows application, including NVIDIA GPU support.
+After installing Ollama Windows Preview, Ollama will run in the background and
+the `ollama` command line is available in `cmd`, `powershell` or your favorite
+terminal application. As usual the Ollama [api](./api.md) will be served on
+`http://localhost:11434`.
+
+As this is a preview release, you should expect a few bugs here and there.  If
+you run into a problem you can reach out on
+[Discord](https://discord.gg/ollama), or file an 
+[issue](https://github.com/ollama/ollama/issues).
+Logs will be often be helpful in dianosing the problem (see
+[Troubleshooting](#troubleshooting) below)
+
+## System Requirements
+
+* Windows 10 or newer, Home or Pro
+* NVIDIA 452.39 or newer Drivers if you have an NVIDIA card
+
+## API Access
+
+Here's a quick example showing API access from `powershell`
+```powershell
+(Invoke-WebRequest -method POST -Body '{"model":"llama2", "prompt":"Why is the sky blue?", "stream": false}' -uri http://localhost:11434/api/generate ).Content | ConvertFrom-json
+```
+
+## Troubleshooting
+
+While we're in preview, `OLLAMA_DEBUG` is always enabled, which adds
+a "view logs" menu item to the app, and increses logging for the GUI app and
+server.
+
+Ollama on Windows stores files in a few different locations.  You can view them in
+the explorer window by hitting `<cmd>+R` and type in:
+- `explorer %LOCALAPPDATA%\Ollama` contains logs, and downloaded updates
+    - *app.log* contains logs from the GUI application
+    - *server.log* contains the server logs
+    - *upgrade.log* contains log output for upgrades
+- `explorer %LOCALAPPDATA%\Programs\Ollama` contains the binaries (The installer adds this to your user PATH)
+- `explorer %HOMEPATH%\.ollama` contains models and configuration
+- `explorer %TEMP%` contains temporary executable files in one or more `ollama*` directories

go.mod

@@ -12,8 +12,20 @@ require (
 )
 
 require (
+	github.com/cratonica/2goarray v0.0.0-20190331194516-514510793eaa // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/getlantern/context v0.0.0-20190109183933-c447772a6520 // indirect
+	github.com/getlantern/errors v0.0.0-20190325191628-abdb3e3e36f7 // indirect
+	github.com/getlantern/golog v0.0.0-20190830074920-4ef2e798c2d7 // indirect
+	github.com/getlantern/hex v0.0.0-20190417191902-c6586a6fe0b7 // indirect
+	github.com/getlantern/hidden v0.0.0-20190325191715-f02dbb02be55 // indirect
+	github.com/getlantern/ops v0.0.0-20190325191751-d70cb0d6f85f // indirect
+	github.com/getlantern/systray v1.2.2 // indirect
+	github.com/go-stack/stack v1.8.0 // indirect
+	github.com/google/uuid v1.0.0 // indirect
 	github.com/mattn/go-runewidth v0.0.14 // indirect
+	github.com/oxtoacart/bpool v0.0.0-20190530202638-03653db5a59c // indirect
+	github.com/pborman/uuid v1.2.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/rivo/uniseg v0.2.0 // indirect
 )

go.sum

@@ -5,6 +5,8 @@ github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
 github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
+github.com/cratonica/2goarray v0.0.0-20190331194516-514510793eaa h1:Wg+722vs7a2zQH5lR9QWYsVbplKeffaQFIs5FTdfNNo=
+github.com/cratonica/2goarray v0.0.0-20190331194516-514510793eaa/go.mod h1:6Arca19mRx58CA7OWEd7Wu1NpC1rd3uDnNs6s1pj/DI=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -13,6 +15,20 @@ github.com/emirpasic/gods v1.18.1 h1:FXtiHYKDGKCW2KzwZKx0iC0PQmdlorYgdFG9jPXJ1Bc
 github.com/emirpasic/gods v1.18.1/go.mod h1:8tpGGwCnJ5H4r6BWwaV6OrWmMoPhUl5jm/FMNAnJvWQ=
 github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
 github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
+github.com/getlantern/context v0.0.0-20190109183933-c447772a6520 h1:NRUJuo3v3WGC/g5YiyF790gut6oQr5f3FBI88Wv0dx4=
+github.com/getlantern/context v0.0.0-20190109183933-c447772a6520/go.mod h1:L+mq6/vvYHKjCX2oez0CgEAJmbq1fbb/oNJIWQkBybY=
+github.com/getlantern/errors v0.0.0-20190325191628-abdb3e3e36f7 h1:6uJ+sZ/e03gkbqZ0kUG6mfKoqDb4XMAzMIwlajq19So=
+github.com/getlantern/errors v0.0.0-20190325191628-abdb3e3e36f7/go.mod h1:l+xpFBrCtDLpK9qNjxs+cHU6+BAdlBaxHqikB6Lku3A=
+github.com/getlantern/golog v0.0.0-20190830074920-4ef2e798c2d7 h1:guBYzEaLz0Vfc/jv0czrr2z7qyzTOGC9hiQ0VC+hKjk=
+github.com/getlantern/golog v0.0.0-20190830074920-4ef2e798c2d7/go.mod h1:zx/1xUUeYPy3Pcmet8OSXLbF47l+3y6hIPpyLWoR9oc=
+github.com/getlantern/hex v0.0.0-20190417191902-c6586a6fe0b7 h1:micT5vkcr9tOVk1FiH8SWKID8ultN44Z+yzd2y/Vyb0=
+github.com/getlantern/hex v0.0.0-20190417191902-c6586a6fe0b7/go.mod h1:dD3CgOrwlzca8ed61CsZouQS5h5jIzkK9ZWrTcf0s+o=
+github.com/getlantern/hidden v0.0.0-20190325191715-f02dbb02be55 h1:XYzSdCbkzOC0FDNrgJqGRo8PCMFOBFL9py72DRs7bmc=
+github.com/getlantern/hidden v0.0.0-20190325191715-f02dbb02be55/go.mod h1:6mmzY2kW1TOOrVy+r41Za2MxXM+hhqTtY3oBKd2AgFA=
+github.com/getlantern/ops v0.0.0-20190325191751-d70cb0d6f85f h1:wrYrQttPS8FHIRSlsrcuKazukx/xqO/PpLZzZXsF+EA=
+github.com/getlantern/ops v0.0.0-20190325191751-d70cb0d6f85f/go.mod h1:D5ao98qkA6pxftxoqzibIBBrLSUli+kYnJqrgBf9cIA=
+github.com/getlantern/systray v1.2.2 h1:dCEHtfmvkJG7HZ8lS/sLklTH4RKUcIsKrAD9sThoEBE=
+github.com/getlantern/systray v1.2.2/go.mod h1:pXFOI1wwqwYXEhLPm9ZGjS2u/vVELeIgNMY5HvhHhcE=
 github.com/gin-contrib/cors v1.4.0 h1:oJ6gwtUl3lqV0WEIwM/LxPF1QZ5qe2lGWdY2+bz7y0g=
 github.com/gin-contrib/cors v1.4.0/go.mod h1:bs9pNM0x/UsmHPBWT2xZz9ROh8xYjYkiURUfmBoMlcs=
 github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE=
@@ -31,6 +47,8 @@ github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91
 github.com/go-playground/validator/v10 v10.10.0/go.mod h1:74x4gJWsvQexRdW8Pn3dXSGrTK4nAUsbPlLADvpJkos=
 github.com/go-playground/validator/v10 v10.14.0 h1:vgvQWe3XCz3gIeFDm/HnTIbj6UGmg/+t63MyGU2n5js=
 github.com/go-playground/validator/v10 v10.14.0/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
+github.com/go-stack/stack v1.8.0 h1:5SgMzNM5HxrEjV0ww2lTmX6E2Izsfxas4+YHWRs3Lsk=
+github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
 github.com/goccy/go-json v0.9.7/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
@@ -39,6 +57,8 @@ github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
 github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
 github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/uuid v1.0.0 h1:b4Gk+7WdP/d3HZH8EJsZpvV7EtDOgaZLtnaNGIu1adA=
+github.com/google/uuid v1.0.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
@@ -57,6 +77,8 @@ github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
 github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
 github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
+github.com/lxn/walk v0.0.0-20210112085537-c389da54e794/go.mod h1:E23UucZGqpuUANJooIbHWCufXvOcT6E7Stq81gU+CSQ=
+github.com/lxn/win v0.0.0-20210218163916-a377121e959e/go.mod h1:KxxjdtRkfNoYDCUP5ryK7XJJNTnpC8atvtmTheChOtk=
 github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
 github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
 github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
@@ -70,8 +92,12 @@ github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9G
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/olekukonko/tablewriter v0.0.5 h1:P2Ga83D34wi1o9J6Wh1mRuqd4mF/x/lgBS7N7AbDhec=
 github.com/olekukonko/tablewriter v0.0.5/go.mod h1:hPp6KlRPjbx+hW8ykQs1w3UBbZlj6HuIJcUGPhkA7kY=
+github.com/oxtoacart/bpool v0.0.0-20190530202638-03653db5a59c h1:rp5dCmg/yLR3mgFuSOe4oEnDDmGLROTvMragMUXpTQw=
+github.com/oxtoacart/bpool v0.0.0-20190530202638-03653db5a59c/go.mod h1:X07ZCGwUbLaax7L0S3Tw4hpejzu63ZrrQiUe6W0hcy0=
 github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58 h1:onHthvaw9LFnH4t2DcNVpwGmV9E1BkGknEliJkfwQj0=
 github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58/go.mod h1:DXv8WO4yhMYhSNPKjeNKa5WY9YCIEBRbNzFFPJbWO6Y=
+github.com/pborman/uuid v1.2.1 h1:+ZZIw58t/ozdjRaXh/3awHfmWRbzYxJoAdNJxe/3pvw=
+github.com/pborman/uuid v1.2.1/go.mod h1:X/NO0urCmaxf9VXbdlT7C2Yzkj2IKimNn4k+gtPdI/k=
 github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
 github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
 github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
@@ -84,6 +110,7 @@ github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTE
 github.com/rogpeppe/go-internal v1.8.0 h1:FCbCCtXNOY3UtUuHUYaghJg4y7Fd14rXifAYUAtL9R8=
 github.com/rogpeppe/go-internal v1.8.0/go.mod h1:WmiCO8CzOY8rg0OYDC4/i/2WRWAB6poM+XZ2dLUbcbE=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/skratchdot/open-golang v0.0.0-20200116055534-eef842397966/go.mod h1:sUM3LWHvSMaG192sy56D9F7CNvL7jUJVXoqM1QKLnog=
 github.com/spf13/cobra v1.7.0 h1:hyqWnYt1ZQShIddO5kBpj3vu05/++x6tJ6dg8EC572I=
 github.com/spf13/cobra v1.7.0/go.mod h1:uLxZILRyS/50WlhOIKD7W6V5bgeIt+4sICxh6uRMrb0=
 github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
@@ -120,11 +147,13 @@ golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
 golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
 golang.org/x/sync v0.3.0 h1:ftCYgMx6zT/asHUrPw8BLLscYtGznsLAnjq5RH9P66E=
 golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
+golang.org/x/sys v0.0.0-20201018230417-eeed37f84f13/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.13.0 h1:Af8nKPmuFypiUBjVoU9V20FiaFXOcuZI21p0ycVYYGE=
 golang.org/x/sys v0.13.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -141,6 +170,7 @@ google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp0
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
 google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+gopkg.in/Knetic/govaluate.v3 v3.0.0/go.mod h1:csKLBORsPbafmSCGTEh3U7Ozmsuq8ZSIlKk1bcqph0E=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=

llm/generate/gen_windows.ps1

@@ -4,7 +4,7 @@ $ErrorActionPreference = "Stop"
 
 function init_vars {
     $script:llamacppDir = "../llama.cpp"
-    $script:cmakeDefs = @("-DBUILD_SHARED_LIBS=on", "-DLLAMA_NATIVE=off",  "-A","x64")
+    $script:cmakeDefs = @("-DBUILD_SHARED_LIBS=on", "-DLLAMA_NATIVE=off",  "-A", "x64")
     $script:cmakeTargets = @("ext_server")
     $script:ARCH = "amd64" # arm not yet supported.
     if ($env:CGO_CFLAGS -contains "-g") {
@@ -19,6 +19,7 @@ function init_vars {
         $d=(get-command -ea 'silentlycontinue' nvcc).path
         if ($d -ne $null) {
             $script:CUDA_LIB_DIR=($d| split-path -parent)
+            $script:CUDA_INCLUDE_DIR=($script:CUDA_LIB_DIR|split-path -parent)+"\include"
         }
     } else {
         $script:CUDA_LIB_DIR=$env:CUDA_LIB_DIR
@@ -30,6 +31,8 @@ function init_vars {
     } else {
         $script:CMAKE_CUDA_ARCHITECTURES=$env:CMAKE_CUDA_ARCHITECTURES
     }
+    # Note: 10 Windows Kit signtool crashes with GCP's plugin
+    ${script:SignTool}="C:\Program Files (x86)\Windows Kits\8.1\bin\x64\signtool.exe"
 }
 
 function git_module_setup {
@@ -56,8 +59,8 @@ function apply_patches {
         }
 
         # Checkout each file
+        Set-Location -Path ${script:llamacppDir}
         foreach ($file in $filePaths) {
-            Set-Location -Path ${script:llamacppDir}
             git checkout $file
         }
     }
@@ -89,13 +92,23 @@ function install {
     md "${script:buildDir}/lib" -ea 0 > $null
     cp "${script:buildDir}/bin/${script:config}/ext_server.dll" "${script:buildDir}/lib"
     cp "${script:buildDir}/bin/${script:config}/llama.dll" "${script:buildDir}/lib"
-
     # Display the dll dependencies in the build log
     if ($script:DUMPBIN -ne $null) {
         & "$script:DUMPBIN" /dependents "${script:buildDir}/bin/${script:config}/ext_server.dll" | select-string ".dll"
     }
 }
 
+function sign {
+    if ("${env:KEY_CONTAINER}") {
+        write-host "Signing ${script:buildDir}/lib/*.dll"
+        foreach ($file in (get-childitem "${script:buildDir}/lib/*.dll")){
+            & "${script:SignTool}" sign /v /fd sha256 /t http://timestamp.digicert.com /f "${env:OLLAMA_CERT}" `
+                /csp "Google Cloud KMS Provider" /kc "${env:KEY_CONTAINER}" $file
+            if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
+        }
+    }
+}
+
 function compress_libs {
     if ($script:GZIP -eq $null) {
         write-host "gzip not installed, not compressing files"
@@ -109,8 +122,23 @@ function compress_libs {
 }
 
 function cleanup {
+    $patches = Get-ChildItem "../patches/*.diff"
+    foreach ($patch in $patches) {
+        # Extract file paths from the patch file
+        $filePaths = Get-Content $patch.FullName | Where-Object { $_ -match '^\+\+\+ ' } | ForEach-Object {
+            $parts = $_ -split ' '
+            ($parts[1] -split '/', 2)[1]
+        }
+
+        # Checkout each file
+        Set-Location -Path ${script:llamacppDir}
+        foreach ($file in $filePaths) {            
+            git checkout $file
+        }
+    }
     Set-Location "${script:llamacppDir}/examples/server"
     git checkout CMakeLists.txt server.cpp
+
 }
 
 init_vars
@@ -129,6 +157,7 @@ $script:buildDir="${script:llamacppDir}/build/windows/${script:ARCH}/cpu"
 write-host "Building LCD CPU"
 build
 install
+sign
 compress_libs
 
 $script:cmakeDefs = $script:commonCpuDefs + @("-DLLAMA_AVX=on", "-DLLAMA_AVX2=off", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=off", "-DLLAMA_F16C=off") + $script:cmakeDefs
@@ -136,6 +165,7 @@ $script:buildDir="${script:llamacppDir}/build/windows/${script:ARCH}/cpu_avx"
 write-host "Building AVX CPU"
 build
 install
+sign
 compress_libs
 
 $script:cmakeDefs = $script:commonCpuDefs + @("-DLLAMA_AVX=on", "-DLLAMA_AVX2=on", "-DLLAMA_AVX512=off", "-DLLAMA_FMA=on", "-DLLAMA_F16C=on") + $script:cmakeDefs
@@ -143,25 +173,22 @@ $script:buildDir="${script:llamacppDir}/build/windows/${script:ARCH}/cpu_avx2"
 write-host "Building AVX2 CPU"
 build
 install
+sign
 compress_libs
 
 if ($null -ne $script:CUDA_LIB_DIR) {
     # Then build cuda as a dynamically loaded library
-    $nvcc = (get-command -ea 'silentlycontinue' nvcc)
-    if ($null -ne $nvcc) {
-        $script:CUDA_VERSION=(get-item ($nvcc | split-path | split-path)).Basename
-    }
+    $nvcc = "$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
     $script:buildDir="${script:llamacppDir}/build/windows/${script:ARCH}/cuda$script:CUDA_VARIANT"
-    $script:cmakeDefs += @("-DLLAMA_CUBLAS=ON", "-DLLAMA_AVX=on", "-DCMAKE_CUDA_ARCHITECTURES=${script:CMAKE_CUDA_ARCHITECTURES}")
+    $script:cmakeDefs += @("-DLLAMA_CUBLAS=ON", "-DLLAMA_AVX=on", "-DCUDAToolkit_INCLUDE_DIR=$script:CUDA_INCLUDE_DIR", "-DCMAKE_CUDA_ARCHITECTURES=${script:CMAKE_CUDA_ARCHITECTURES}")
     build
     install
-    cp "${script:CUDA_LIB_DIR}/cudart64_*.dll" "${script:buildDir}/lib"
-    cp "${script:CUDA_LIB_DIR}/cublas64_*.dll" "${script:buildDir}/lib"
-    cp "${script:CUDA_LIB_DIR}/cublasLt64_*.dll" "${script:buildDir}/lib"
+    sign
     compress_libs
 }
 # TODO - actually implement ROCm support on windows
@@ -172,4 +199,4 @@ md "${script:buildDir}/lib" -ea 0 > $null
 echo $null >> "${script:buildDir}/lib/.generated"
 
 cleanup
-write-host "`ngo generate completed"
\ No newline at end of file
+write-host "`ngo generate completed"

scripts/build_remote.py

@@ -60,13 +60,17 @@ subprocess.check_call(['ssh', netloc, 'cd', path, ';', 'git', 'checkout', branch
 # subprocess.check_call(['ssh', netloc, 'cd', path, ';', 'env'])
 # TODO - or consider paramiko maybe
 
-print("Performing generate")
-subprocess.check_call(['ssh', netloc, 'cd', path, ';', GoCmd, 'generate', './...'])
+print("Running Windows Build Script")
+subprocess.check_call(['ssh', netloc, 'cd', path, ';', "powershell", "-ExecutionPolicy", "Bypass", "-File", "./scripts/build_windows.ps1"])
 
-print("Building")
-subprocess.check_call(['ssh', netloc, 'cd', path, ';', GoCmd, 'build', '.'])
+# print("Building")
+# subprocess.check_call(['ssh', netloc, 'cd', path, ';', GoCmd, 'build', '.'])
 
 print("Copying built result")
 subprocess.check_call(['scp', netloc +":"+ path + "/ollama.exe",  './dist/'])
 
+print("Copying installer")
+subprocess.check_call(['scp', netloc +":"+ path + "/dist/Ollama Setup.exe",  './dist/'])
+
+
 

scripts/build_windows.ps1

+#!powershell
+#
+# powershell -ExecutionPolicy Bypass -File .\scripts\build_windows.ps1
+#
+# gcloud auth application-default login
+
+$ErrorActionPreference = "Stop"
+
+function checkEnv() {
+    write-host "Locating required tools and paths"
+    $script:SRC_DIR=$PWD
+    if (!$env:VCToolsRedistDir) {
+        $MSVC_INSTALL=(Get-CimInstance MSFT_VSInstance -Namespace root/cimv2/vs)[0].InstallLocation
+        $env:VCToolsRedistDir=(get-item "${MSVC_INSTALL}\VC\Redist\MSVC\*")[0]
+    }
+    $script:NVIDIA_DIR=(get-item "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v*\bin\")[0]
+    $script:INNO_SETUP_DIR=(get-item "C:\Program Files*\Inno Setup*\")[0]
+
+    $script:DEPS_DIR="${script:SRC_DIR}\dist\windeps"
+    $env:CGO_ENABLED="1"
+    echo "Checking version"
+    if (!$env:VERSION) {
+        $data=(git describe --tags --first-parent --abbrev=7 --long --dirty --always)
+        $pattern="v(.+)"
+        if ($data -match $pattern) {
+            $script:VERSION=$matches[1]
+        }
+    } else {
+        $script:VERSION=$env:VERSION
+    }
+    $pattern = "(\d+[.]\d+[.]\d+)-(\d+)-"
+    if ($script:VERSION -match $pattern) {
+        $script:PKG_VERSION=$matches[1] + "." + $matches[2]
+    } else {
+        $script:PKG_VERSION=$script:VERSION
+    }
+    write-host "Building Ollama $script:VERSION with package version $script:PKG_VERSION"
+
+    # Check for signing key
+    if ("${env:KEY_CONTAINER}") {
+        ${env:OLLAMA_CERT}=$(resolve-path "${script:SRC_DIR}\ollama_inc.crt")
+        Write-host "Code signing enabled"
+        # Note: 10 Windows Kit signtool crashes with GCP's plugin
+        ${script:SignTool}="C:\Program Files (x86)\Windows Kits\8.1\bin\x64\signtool.exe"
+    } else {
+        write-host "Code signing disabled - please set KEY_CONTAINERS to sign and copy ollama_inc.crt to the top of the source tree"
+    }
+
+}
+
+
+function buildOllama() {
+    write-host "Building ollama CLI"
+    & go generate ./...
+    if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
+    & go build "-ldflags=-w -s ""-X=github.com/jmorganca/ollama/version.Version=$script:VERSION"" ""-X=github.com/jmorganca/ollama/server.mode=release""" .
+    if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
+    if ("${env:KEY_CONTAINER}") {
+        & "${script:SignTool}" sign /v /fd sha256 /t http://timestamp.digicert.com /f "${env:OLLAMA_CERT}" `
+            /csp "Google Cloud KMS Provider" /kc ${env:KEY_CONTAINER} ollama.exe
+        if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
+    }
+}
+
+function buildApp() {
+    write-host "Building Ollama App"
+    cd "${script:SRC_DIR}\app"
+    & go build "-ldflags=-H windowsgui -w -s ""-X=github.com/jmorganca/ollama/version.Version=$script:VERSION"" ""-X=github.com/jmorganca/ollama/server.mode=release""" .
+    if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
+    if ("${env:KEY_CONTAINER}") {
+        & "${script:SignTool}" sign /v /fd sha256 /t http://timestamp.digicert.com /f "${env:OLLAMA_CERT}" `
+            /csp "Google Cloud KMS Provider" /kc ${env:KEY_CONTAINER} app.exe
+        if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
+    }
+}
+
+function gatherDependencies() {
+    write-host "Gathering runtime dependencies"
+    cd "${script:SRC_DIR}"
+    rm -ea 0 -recurse -force -path "${script:DEPS_DIR}"
+    md "${script:DEPS_DIR}" -ea 0 > $null
+
+    # TODO - this varies based on host build system and MSVC version - drive from dumpbin output
+    # currently works for Win11 + MSVC 2019 + Cuda V11
+    cp "${env:VCToolsRedistDir}\x64\Microsoft.VC*.CRT\msvcp140.dll" "${script:DEPS_DIR}\"
+    cp "${env:VCToolsRedistDir}\x64\Microsoft.VC*.CRT\vcruntime140.dll" "${script:DEPS_DIR}\"
+    cp "${env:VCToolsRedistDir}\x64\Microsoft.VC*.CRT\vcruntime140_1.dll" "${script:DEPS_DIR}\"
+
+    cp "${script:NVIDIA_DIR}\cudart64_*.dll" "${script:DEPS_DIR}\"
+    cp "${script:NVIDIA_DIR}\cublas64_*.dll" "${script:DEPS_DIR}\"
+    cp "${script:NVIDIA_DIR}\cublasLt64_*.dll" "${script:DEPS_DIR}\"
+
+    cp "${script:SRC_DIR}\app\ollama_welcome.ps1" "${script:SRC_DIR}\dist\"
+    if ("${env:KEY_CONTAINER}") {
+        write-host "about to sign"
+        foreach ($file in (get-childitem "${script:DEPS_DIR}/cu*.dll") + @("${script:SRC_DIR}\dist\ollama_welcome.ps1")){
+            write-host "signing $file"
+            & "${script:SignTool}" sign /v /fd sha256 /t http://timestamp.digicert.com /f "${env:OLLAMA_CERT}" `
+                /csp "Google Cloud KMS Provider" /kc ${env:KEY_CONTAINER} $file
+            if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
+        }
+    }
+
+}
+
+function buildInstaller() {
+    write-host "Building Ollama Installer"
+    cd "${script:SRC_DIR}\app"
+    $env:PKG_VERSION=$script:PKG_VERSION
+    if ("${env:KEY_CONTAINER}") {
+        & "${script:INNO_SETUP_DIR}\ISCC.exe" /SMySignTool="${script:SignTool} sign /fd sha256 /t http://timestamp.digicert.com /f ${env:OLLAMA_CERT} /csp `$qGoogle Cloud KMS Provider`$q /kc ${env:KEY_CONTAINER} `$f" .\ollama.iss
+    } else {
+        & "${script:INNO_SETUP_DIR}\ISCC.exe" .\ollama.iss
+    }
+    if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
+}
+
+try {
+    checkEnv
+    buildOllama
+    buildApp
+    gatherDependencies
+    buildInstaller
+} catch {
+    write-host "Build Failed"
+    write-host $_
+} finally {
+    set-location $script:SRC_DIR
+    $env:PKG_VERSION=""
+}
\ No newline at end of file