-
Notifications
You must be signed in to change notification settings - Fork 357
396 lines (362 loc) · 14.9 KB
/
compile.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
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
117
118
119
120
121
122
123
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
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
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
name: Update Binaries
on:
workflow_dispatch:
inputs:
llama_cpp_commit:
description: 'Branch, tag, or commit to use for llama.cpp'
required: true
default: 'master'
push:
branches: [cron_job]
#schedule:
# - cron: "22 22 * * 2"
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.event.inputs.llama_cpp_commit }}
cancel-in-progress: true
env:
# Compiler defines common to all platforms
COMMON_DEFINE: -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_EXAMPLES=ON -DLLAMA_BUILD_SERVER=OFF -DBUILD_SHARED_LIBS=ON -DGGML_RPC=ON
jobs:
compile-linux:
name: Compile (Linux)
strategy:
fail-fast: true
matrix:
include:
- build: 'noavx'
defines: '-DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF'
- build: 'avx2'
defines: ''
- build: 'avx'
defines: '-DLLAMA_AVX2=OFF'
- build: 'avx512'
defines: '-DLLAMA_AVX512=ON'
runs-on: ubuntu-20.04
steps:
- uses: actions/checkout@v4
with:
repository: ggerganov/llama.cpp
fetch-depth: 0
ref: '${{ github.event.inputs.llama_cpp_commit }}'
- name: Build
id: cmake_build
run: |
mkdir build
cd build
cmake .. ${{ env.COMMON_DEFINE }} ${{ matrix.defines }}
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
ls -R
- uses: actions/upload-artifact@v4
with:
path: ./build/src/libllama.so
name: llama-bin-linux-${{ matrix.build }}-x64.so
if-no-files-found: error
- name: Upload Llava
uses: actions/upload-artifact@v4
with:
path: ./build/examples/llava/libllava_shared.so
name: llava-bin-linux-${{ matrix.build }}-x64.so
if-no-files-found: error
compile-windows:
name: Compile (Windows)
strategy:
fail-fast: true
matrix:
include:
- build: 'noavx'
defines: '-DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF'
- build: 'avx2'
defines: ''
- build: 'avx'
defines: '-DLLAMA_AVX2=OFF'
- build: 'avx512'
defines: '-DLLAMA_AVX512=ON -DLLAMA_AVX512_VBMI=ON -DLLAMA_AVX512_VNNI=ON'
runs-on: windows-latest
steps:
- uses: actions/checkout@v4
with:
repository: ggerganov/llama.cpp
fetch-depth: 0
ref: '${{ github.event.inputs.llama_cpp_commit }}'
- name: Build
id: cmake_build
run: |
mkdir build
cd build
cmake .. ${{ env.COMMON_DEFINE }} ${{ matrix.defines }}
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
path: .\build\bin\Release\llama.dll
name: llama-bin-win-${{ matrix.build }}-x64.dll
if-no-files-found: error
- name: Upload Llava
uses: actions/upload-artifact@v4
with:
path: .\build\bin\Release\llava_shared.dll
name: llava-bin-win-${{ matrix.build }}-x64.dll
if-no-files-found: error
compile-vulkan:
name: Compile (vulkan) - ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [
ubuntu-22.04,
windows-latest
]
env:
VULKAN_VERSION: 1.3.261.1
runs-on: ${{ matrix.os }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
with:
repository: ggerganov/llama.cpp
fetch-depth: 0
ref: '${{ github.event.inputs.llama_cpp_commit }}'
- name: Download dependencies - Linux
if: ${{ matrix.os == 'ubuntu-22.04' }}
run: |
wget -qO- https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo tee /etc/apt/trusted.gpg.d/lunarg.asc
sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list http://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list
sudo apt update
sudo apt install vulkan-sdk
- name: Download dependencies - Windows
id: get_vulkan
if: ${{ matrix.os == 'windows-latest' }}
run: |
curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe"
& "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"
- name: Build
id: cmake_build
if: ${{ matrix.os == 'windows-latest' }}
run: |
mkdir build
cd build
cmake .. ${{ env.COMMON_DEFINE }} -DLLAMA_VULKAN=ON
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
ls -R
- name: Build
if: ${{ matrix.os == 'ubuntu-22.04' }}
run: |
mkdir build
cd build
cmake .. ${{ env.COMMON_DEFINE }} -DLLAMA_VULKAN=ON
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
ls -R
- name: Upload llama artifacts (Windows)
if: ${{ matrix.os == 'windows-latest' }}
uses: actions/upload-artifact@v4
with:
path: .\build\bin\Release\llama.dll
name: llama-bin-win-vulkan-x64.dll
if-no-files-found: error
- name: Upload llava artifacts (Windows)
if: ${{ matrix.os == 'windows-latest' }}
uses: actions/upload-artifact@v4
with:
path: .\build\bin\Release\llava_shared.dll
name: llava-bin-win-vulkan-x64.dll
if-no-files-found: error
- name: Upload llama artifacts (Linux)
if: ${{ matrix.os == 'ubuntu-22.04' }}
uses: actions/upload-artifact@v4
with:
path: ./build/src/libllama.so
name: llama-bin-linux-vulkan-x64.so
if-no-files-found: error
- name: Upload llava artifacts (Linux)
if: ${{ matrix.os == 'ubuntu-22.04' }}
uses: actions/upload-artifact@v4
with:
path: ./build/examples/llava/libllava_shared.so
name: llava-bin-linux-vulkan-x64.so
if-no-files-found: error
compile-cublas:
name: Compile (cublas)
strategy:
fail-fast: false
matrix:
os: [ubuntu-20.04, windows-2019]
cuda: ['12.2.0', '11.7.1']
runs-on: ${{ matrix.os }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
with:
repository: ggerganov/llama.cpp
fetch-depth: 0
ref: '${{ github.event.inputs.llama_cpp_commit }}'
- uses: Jimver/cuda-toolkit@v0.2.15
if: runner.os == 'Windows'
id: cuda-toolkit-windows
with:
cuda: ${{ matrix.cuda }}
method: 'network'
sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
- uses: Jimver/cuda-toolkit@v0.2.15
if: runner.os == 'Linux'
id: cuda-toolkit-linux
with:
cuda: ${{ matrix.cuda }}
method: 'network'
linux-local-args: '["--toolkit"]'
- name: Build
id: cmake_build
run: |
mkdir build
cd build
cmake .. ${{ env.COMMON_DEFINE }} -DGGML_CUDA=ON
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
ls -R
- name: Upload artifacts (Windows)
if: ${{ matrix.os == 'windows-2019' }}
uses: actions/upload-artifact@v4
with:
path: .\build\bin\Release\llama.dll
name: llama-bin-win-cublas-cu${{ matrix.cuda }}-x64.dll
if-no-files-found: error
- name: Upload llava artifacts (Windows)
if: ${{ matrix.os == 'windows-2019' }}
uses: actions/upload-artifact@v4
with:
path: .\build\bin\Release\llava_shared.dll
name: llava-bin-win-cublas-cu${{ matrix.cuda }}-x64.dll
if-no-files-found: error
- name: Upload artifacts (Linux)
if: ${{ matrix.os == 'ubuntu-20.04' }}
uses: actions/upload-artifact@v4
with:
path: ./build/src/libllama.so
name: llama-bin-linux-cublas-cu${{ matrix.cuda }}-x64.so
if-no-files-found: error
- name: Upload llava artifacts (Linux)
if: ${{ matrix.os == 'ubuntu-20.04' }}
uses: actions/upload-artifact@v4
with:
path: ./build/examples/llava/libllava_shared.so
name: llava-bin-linux-cublas-cu${{ matrix.cuda }}-x64.so
if-no-files-found: error
compile-macos:
name: Compile (MacOS)
strategy:
fail-fast: true
matrix:
include:
- build: 'arm64'
defines: '-DCMAKE_OSX_ARCHITECTURES=arm64 -DGGML_METAL_EMBED_LIBRARY=ON'
- build: 'x64'
defines: '-DCMAKE_OSX_ARCHITECTURES=x86_64 -DGGML_METAL=OFF -DLLAMA_AVX=ON -DLLAMA_AVX2=ON'
- build: 'x64-rosetta2'
defines: '-DCMAKE_OSX_ARCHITECTURES=x86_64 -DGGML_METAL=OFF -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF'
runs-on: macos-latest
steps:
- uses: actions/checkout@v4
with:
repository: ggerganov/llama.cpp
fetch-depth: 0
ref: '${{ github.event.inputs.llama_cpp_commit }}'
- name: Dependencies
continue-on-error: true
run: |
brew update
- name: Build
id: cmake_build
run: |
mkdir build
cd build
cmake .. ${{ env.COMMON_DEFINE }} ${{ matrix.defines }}
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
path: ./build/src/libllama.dylib
name: llama-bin-osx-${{ matrix.build }}.dylib
if-no-files-found: error
- name: Upload Llava
uses: actions/upload-artifact@v4
with:
path: ./build/examples/llava/libllava_shared.dylib
name: llava-bin-osx-${{ matrix.build }}.dylib
if-no-files-found: error
- name: Upload Metal
if: ${{ matrix.build == 'arm64' }}
uses: actions/upload-artifact@v4
with:
path: ./build/bin/ggml-metal.metal
name: ggml-metal.metal
if-no-files-found: error
build-deps:
runs-on: ubuntu-latest
name: "Gather Binaries"
if: ${{ always() }}
needs: [
"compile-linux",
"compile-macos",
"compile-windows",
"compile-cublas",
"compile-vulkan"
]
steps:
- uses: actions/download-artifact@v4
with:
path: artifacts
- name: List Files
run: ls -R
- name: Rearrange Files
run: |
# Make all directories at once
mkdir --parents deps/{avx,avx2,avx512,osx-arm64,osx-x64,osx-x64-rosetta2,cu11.7.1,cu12.2.0,vulkan}
cp artifacts/llama-bin-linux-noavx-x64.so/libllama.so deps/libllama.so
cp artifacts/llama-bin-linux-avx-x64.so/libllama.so deps/avx/libllama.so
cp artifacts/llama-bin-linux-avx2-x64.so/libllama.so deps/avx2/libllama.so
cp artifacts/llama-bin-linux-avx512-x64.so/libllama.so deps/avx512/libllama.so
cp artifacts/llama-bin-win-noavx-x64.dll/llama.dll deps/llama.dll
cp artifacts/llama-bin-win-avx-x64.dll/llama.dll deps/avx/llama.dll
cp artifacts/llama-bin-win-avx2-x64.dll/llama.dll deps/avx2/llama.dll
cp artifacts/llama-bin-win-avx512-x64.dll/llama.dll deps/avx512/llama.dll
cp artifacts/llava-bin-linux-noavx-x64.so/libllava_shared.so deps/libllava_shared.so
cp artifacts/llava-bin-linux-avx-x64.so/libllava_shared.so deps/avx/libllava_shared.so
cp artifacts/llava-bin-linux-avx2-x64.so/libllava_shared.so deps/avx2/libllava_shared.so
cp artifacts/llava-bin-linux-avx512-x64.so/libllava_shared.so deps/avx512/libllava_shared.so
cp artifacts/llava-bin-win-noavx-x64.dll/llava_shared.dll deps/llava_shared.dll
cp artifacts/llava-bin-win-avx-x64.dll/llava_shared.dll deps/avx/llava_shared.dll
cp artifacts/llava-bin-win-avx2-x64.dll/llava_shared.dll deps/avx2/llava_shared.dll
cp artifacts/llava-bin-win-avx512-x64.dll/llava_shared.dll deps/avx512/llava_shared.dll
cp artifacts/llama-bin-osx-arm64.dylib/libllama.dylib deps/osx-arm64/libllama.dylib
cp artifacts/llava-bin-osx-arm64.dylib/libllava_shared.dylib deps/osx-arm64/libllava_shared.dylib
cp artifacts/ggml-metal.metal/ggml-metal.metal deps/osx-arm64/ggml-metal.metal
cp artifacts/llama-bin-osx-x64.dylib/libllama.dylib deps/osx-x64/libllama.dylib
cp artifacts/llava-bin-osx-x64.dylib/libllava_shared.dylib deps/osx-x64/libllava_shared.dylib
cp artifacts/llama-bin-osx-x64-rosetta2.dylib/libllama.dylib deps/osx-x64-rosetta2/libllama.dylib
cp artifacts/llava-bin-osx-x64-rosetta2.dylib/libllava_shared.dylib deps/osx-x64-rosetta2/libllava_shared.dylib
cp artifacts/llama-bin-win-cublas-cu11.7.1-x64.dll/llama.dll deps/cu11.7.1/llama.dll
cp artifacts/llava-bin-win-cublas-cu11.7.1-x64.dll/llava_shared.dll deps/cu11.7.1/llava_shared.dll
cp artifacts/llama-bin-linux-cublas-cu11.7.1-x64.so/libllama.so deps/cu11.7.1/libllama.so
cp artifacts/llava-bin-linux-cublas-cu11.7.1-x64.so/libllava_shared.so deps/cu11.7.1/libllava_shared.so
cp artifacts/llama-bin-win-cublas-cu12.2.0-x64.dll/llama.dll deps/cu12.2.0/llama.dll
cp artifacts/llava-bin-win-cublas-cu12.2.0-x64.dll/llava_shared.dll deps/cu12.2.0/llava_shared.dll
cp artifacts/llama-bin-linux-cublas-cu12.2.0-x64.so/libllama.so deps/cu12.2.0/libllama.so
cp artifacts/llava-bin-linux-cublas-cu12.2.0-x64.so/libllava_shared.so deps/cu12.2.0/libllava_shared.so
cp artifacts/llama-bin-win-vulkan-x64.dll/llama.dll deps/vulkan/llama.dll
cp artifacts/llava-bin-win-vulkan-x64.dll/llava_shared.dll deps/vulkan/llava_shared.dll
cp artifacts/llama-bin-linux-vulkan-x64.so/libllama.so deps/vulkan/libllama.so
cp artifacts/llava-bin-linux-vulkan-x64.so/libllava_shared.so deps/vulkan/libllava_shared.so
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
path: deps/
name: deps
- name: Remove Artifacts
uses: geekyeggo/delete-artifact@v5
with:
name: |
llama-*
llava-*
*.metal