Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
orangecat
ollama
Commits
0cb78a2f
Commit
0cb78a2f
authored
Dec 06, 2024
by
xuxzh1
🎱
Browse files
update
parent
217903ab
Changes
288
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
620 additions
and
0 deletions
+620
-0
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu
...emplate-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu
...emplate-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu
...emplate-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu
...emplate-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu
...emplate-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu
...emplate-instances/fattn-vec-f32-instance-hs128-f16-f16.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu
...mplate-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu
...mplate-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu
...mplate-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu
...mplate-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu
...mplate-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu
...mplate-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu
...plate-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu
...plate-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu
...plate-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu
...plate-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu
...plate-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu
...mplate-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu
...plate-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu
+31
-0
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu
...plate-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu
+31
-0
No files found.
Too many changes to show.
To preserve performance only
288 of 288+
files are displayed.
Plain diff
Email patch
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE
(
64
,
GGML_TYPE_F16
,
GGML_TYPE_Q4_0
);
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE
(
64
,
GGML_TYPE_F16
,
GGML_TYPE_Q4_1
);
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE
(
64
,
GGML_TYPE_F16
,
GGML_TYPE_Q5_0
);
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE
(
64
,
GGML_TYPE_F16
,
GGML_TYPE_Q5_1
);
llama/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE
(
64
,
GGML_TYPE_F16
,
GGML_TYPE_Q8_0
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_F16
,
GGML_TYPE_F16
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_F16
,
GGML_TYPE_Q4_0
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_F16
,
GGML_TYPE_Q4_1
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_F16
,
GGML_TYPE_Q5_0
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_F16
,
GGML_TYPE_Q5_1
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_F16
,
GGML_TYPE_Q8_0
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_0
,
GGML_TYPE_F16
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_0
,
GGML_TYPE_Q4_0
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_0
,
GGML_TYPE_Q4_1
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_0
,
GGML_TYPE_Q5_0
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_0
,
GGML_TYPE_Q5_1
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_0
,
GGML_TYPE_Q8_0
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_1
,
GGML_TYPE_F16
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_1
,
GGML_TYPE_Q4_0
);
llama/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu
0 → 100644
View file @
0cb78a2f
/**
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
*
* MIT License
*
* Copyright (c) 2023-2024 The ggml authors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE
(
128
,
GGML_TYPE_Q4_1
,
GGML_TYPE_Q4_1
);
Prev
1
…
10
11
12
13
14
15
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment