gen_windows.ps1 17.1 KB
Newer Older
mashun1's avatar
v1  
mashun1 committed
1
2
3
4
5
6
7
8
#!powershell

$ErrorActionPreference = "Stop"

function amdGPUs {
    if ($env:AMDGPU_TARGETS) {
        return $env:AMDGPU_TARGETS
    }
xuxzh1's avatar
init  
xuxzh1 committed
9
10
    # Current supported rocblas list from ROCm v6.1.2 on windows
    # https://rocm.docs.amd.com/projects/install-on-windows/en/latest/reference/system-requirements.html#windows-supported-gpus
mashun1's avatar
v1  
mashun1 committed
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
    $GPU_LIST = @(
        "gfx1030"
        "gfx1100"
        "gfx1101"
        "gfx1102"
    )
    $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:cmakeDefs = @(
        "-DBUILD_SHARED_LIBS=on",
xuxzh1's avatar
init  
xuxzh1 committed
33
34
        "-DGGML_NATIVE=off",
        "-DGGML_OPENMP=off"
mashun1's avatar
v1  
mashun1 committed
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
        )
    $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 > $null
    if ($env:CGO_CFLAGS -contains "-g") {
        $script:cmakeDefs += @("-DCMAKE_VERBOSE_MAKEFILE=on", "-DLLAMA_SERVER_VERBOSE=on", "-DCMAKE_BUILD_TYPE=RelWithDebInfo")
        $script:config = "RelWithDebInfo"
    } else {
        $script:cmakeDefs += @("-DLLAMA_SERVER_VERBOSE=off", "-DCMAKE_BUILD_TYPE=Release")
        $script:config = "Release"
    }
    if ($null -ne $env:CMAKE_SYSTEM_VERSION) {
        $script:cmakeDefs += @("-DCMAKE_SYSTEM_VERSION=${env:CMAKE_SYSTEM_VERSION}")
    }
    # Try to find the CUDA dir
    if ($env:CUDA_LIB_DIR -eq $null) {
        $d=(get-command -ea 'silentlycontinue' nvcc).path
        if ($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
    }
    $script:DUMPBIN=(get-command -ea 'silentlycontinue' dumpbin).path
    if ($null -eq $env:CMAKE_CUDA_ARCHITECTURES) {
        $script:CMAKE_CUDA_ARCHITECTURES="50;52;61;70;75;80"
    } else {
        $script:CMAKE_CUDA_ARCHITECTURES=$env:CMAKE_CUDA_ARCHITECTURES
    }
    # Note: Windows Kits 10 signtool crashes with GCP's plugin
    if ($null -eq $env:SIGN_TOOL) {
        ${script:SignTool}="C:\Program Files (x86)\Windows Kits\8.1\bin\x64\signtool.exe"
    } else {
        ${script:SignTool}=${env:SIGN_TOOL}
    }
    if ("${env:KEY_CONTAINER}") {
        ${script:OLLAMA_CERT}=$(resolve-path "${script:SRC_DIR}\ollama_inc.crt")
    }
}

function git_module_setup {
    # TODO add flags to skip the init/patch logic to make it easier to mod llama.cpp code in-repo
    & git submodule init
    if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
    & git submodule update --force "${script:llamacppDir}"
    if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
}

function apply_patches {
    # Wire up our CMakefile
    if (!(Select-String -Path "${script:llamacppDir}/CMakeLists.txt" -Pattern 'ollama')) {
        Add-Content -Path "${script:llamacppDir}/CMakeLists.txt" -Value 'add_subdirectory(../ext_server ext_server) # ollama'
    }

    # Apply temporary patches until fix is upstream
    $patches = Get-ChildItem "../patches/*.diff"
    foreach ($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
        foreach ($file in $filePaths) {
            git -C "${script:llamacppDir}" checkout $file
        }
    }

    # Apply each patch
    foreach ($patch in $patches) {
        git -C "${script:llamacppDir}" apply $patch.FullName
    }
}

function build {
    write-host "generating config with: cmake -S ${script:llamacppDir} -B $script:buildDir $script:cmakeDefs"
    & cmake --version
    & cmake -S "${script:llamacppDir}" -B $script:buildDir $script:cmakeDefs
    if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
xuxzh1's avatar
init  
xuxzh1 committed
117
118
119
120
121
122
123
    if ($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", $_ }) $extra
mashun1's avatar
v1  
mashun1 committed
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
    if ($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/${script:config}" ) ) {
        mv -force "${script:buildDir}/bin/${script:config}/*" "${script:buildDir}/bin/"
        remove-item "${script:buildDir}/bin/${script:config}"
    }
}

function sign {
    if ("${env:KEY_CONTAINER}") {
        write-host "Signing ${script:buildDir}/bin/*.exe  ${script:buildDir}/bin/*.dll"
        foreach ($file in @(get-childitem "${script:buildDir}/bin/*.exe") + @(get-childitem "${script:buildDir}/bin/*.dll")){
            & "${script:SignTool}" sign /v /fd sha256 /t http://timestamp.digicert.com /f "${script:OLLAMA_CERT}" `
                /csp "Google Cloud KMS Provider" /kc "${env:KEY_CONTAINER}" $file
            if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
        }
    }
}

function install {
    write-host "Installing binaries to dist dir ${script:distDir}"
    mkdir ${script:distDir} -ErrorAction SilentlyContinue
    $binaries = dir "${script:buildDir}/bin/*.exe"
    foreach ($file in $binaries) {
        copy-item -Path $file -Destination ${script:distDir} -Force
    }

    write-host "Installing dlls to dist dir ${script:distDir}"
    $dlls = dir "${script:buildDir}/bin/*.dll"
    foreach ($file in $dlls) {
        copy-item -Path $file -Destination ${script:distDir} -Force
    }
}

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
        foreach ($file in $filePaths) {            
            git -C "${script:llamacppDir}" checkout $file
        }
        git -C "${script:llamacppDir}" checkout CMakeLists.txt
    }
}


xuxzh1's avatar
init  
xuxzh1 committed
176
177
178
# -DGGML_AVX -- 2011 Intel Sandy Bridge & AMD Bulldozer
# -DGGML_AVX2 -- 2013 Intel Haswell & 2015 AMD Excavator / 2017 AMD Zen
# -DGGML_FMA (FMA3) -- 2013 Intel Haswell & 2012 AMD Piledriver
mashun1's avatar
v1  
mashun1 committed
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197


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",
xuxzh1's avatar
init  
xuxzh1 committed
198
199
200
201
202
203
204
            "-DGGML_NATIVE=off",
            "-DGGML_AVX=off",
            "-DGGML_AVX2=off",
            "-DGGML_AVX512=off",
            "-DGGML_F16C=off",
            "-DGGML_FMA=off",
            "-DGGML_OPENMP=off")
mashun1's avatar
v1  
mashun1 committed
205
206
207
208
209
210
211
212
213
214
215
216
217
        $script:buildDir="../build/windows/${script:ARCH}_static"
        write-host "Building static library"
        build
        $script:cmakeTargets = $oldTargets
    } else {
        write-host "Skipping CPU generation step as requested"
    }
}

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
xuxzh1's avatar
init  
xuxzh1 committed
218
        $script:cmakeDefs = $script:commonCpuDefs + @("-A", $gen_arch, "-DGGML_AVX=off", "-DGGML_AVX2=off", "-DGGML_AVX512=off", "-DGGML_FMA=off", "-DGGML_F16C=off") + $script:cmakeDefs
mashun1's avatar
v1  
mashun1 committed
219
220
221
222
223
224
225
226
227
228
229
230
231
232
        $script:buildDir="../build/windows/${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
xuxzh1's avatar
init  
xuxzh1 committed
233
        $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DGGML_AVX=on", "-DGGML_AVX2=off", "-DGGML_AVX512=off", "-DGGML_FMA=off", "-DGGML_F16C=off") + $script:cmakeDefs
mashun1's avatar
v1  
mashun1 committed
234
235
236
237
238
239
240
241
242
243
244
245
246
247
        $script:buildDir="../build/windows/${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
xuxzh1's avatar
init  
xuxzh1 committed
248
        $script:cmakeDefs = $script:commonCpuDefs + @("-A", "x64", "-DGGML_AVX=on", "-DGGML_AVX2=on", "-DGGML_AVX512=off", "-DGGML_FMA=on", "-DGGML_F16C=on") + $script:cmakeDefs
mashun1's avatar
v1  
mashun1 committed
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
        $script:buildDir="../build/windows/${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"
xuxzh1's avatar
init  
xuxzh1 committed
271
272
273
274
275
276
277
278
279
        $script:cmakeDefs += @(
            "-A", "x64",
            "-DGGML_CUDA=ON",
            "-DGGML_AVX=on",
            "-DGGML_AVX2=off",
            "-DCUDAToolkit_INCLUDE_DIR=$script:CUDA_INCLUDE_DIR",
            "-DCMAKE_CUDA_FLAGS=-t8",
            "-DCMAKE_CUDA_ARCHITECTURES=${script:CMAKE_CUDA_ARCHITECTURES}"
            )
mashun1's avatar
v1  
mashun1 committed
280
281
282
283
284
285
286
287
288
        if ($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

xuxzh1's avatar
init  
xuxzh1 committed
289
290
291
292
293
294
        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\"
mashun1's avatar
v1  
mashun1 committed
295
296
297
298
299
300
    } else {
        write-host "Skipping CUDA generation step"
    }
}

function build_oneapi() {
xuxzh1's avatar
init  
xuxzh1 committed
301
  if ((-not "${env:OLLAMA_SKIP_ONEAPI_GENERATE}") -and ("${env:ONEAPI_ROOT}"))  {
mashun1's avatar
v1  
mashun1 committed
302
303
304
305
306
307
308
309
310
311
312
    # Get oneAPI version
    $script:ONEAPI_VERSION = icpx --version
    $script:ONEAPI_VERSION = [regex]::Match($script:ONEAPI_VERSION, '(?<=oneAPI DPC\+\+/C\+\+ Compiler )(?<version>\d+\.\d+\.\d+)').Value
    if ($null -ne $script:ONEAPI_VERSION) {
      $script:ONEAPI_VARIANT = "_v" + $script:ONEAPI_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",
xuxzh1's avatar
init  
xuxzh1 committed
313
      "-DGGML_SYCL=ON",
mashun1's avatar
v1  
mashun1 committed
314
315
316
317
318
319
320
321
322
323
324
325
326
327
      "-DCMAKE_C_COMPILER=icx",
      "-DCMAKE_CXX_COMPILER=icx",
      "-DCMAKE_BUILD_TYPE=Release"
    )

    Write-Host "Building oneAPI"
    build
    # Ninja doesn't prefix with config name
    if ($null -ne $script:DUMPBIN) {
      & "$script:DUMPBIN" /dependents "${script:buildDir}/bin/ollama_llama_server.exe" | Select-String ".dll"
    }
    sign
    install

xuxzh1's avatar
init  
xuxzh1 committed
328
329
330
331
332
333
334
335
336
337
338
339
    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\"
mashun1's avatar
v1  
mashun1 committed
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
  } else {
    Write-Host "Skipping oneAPI generation step"
  }
}

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"
        $script:cmakeDefs += @(
            "-G", "Ninja", 
            "-DCMAKE_C_COMPILER=clang.exe",
            "-DCMAKE_CXX_COMPILER=clang++.exe",
xuxzh1's avatar
init  
xuxzh1 committed
359
360
            "-DGGML_HIPBLAS=on",
            "-DLLAMA_CUDA_NO_PEER_COPY=on",
mashun1's avatar
v1  
mashun1 committed
361
            "-DHIP_PLATFORM=amd",
xuxzh1's avatar
init  
xuxzh1 committed
362
363
            "-DGGML_AVX=on",
            "-DGGML_AVX2=off",
mashun1's avatar
v1  
mashun1 committed
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
            "-DCMAKE_POSITION_INDEPENDENT_CODE=on",
            "-DAMDGPU_TARGETS=$(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

        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])
    } 
}