vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add autogenerated .cu files

Browse source
This commit is contained in:
Johannes Gäßler 2024-05-29 20:14:31 +02:00
parent 2eb0f7f7e8
commit 62056fa679
91 changed files with 477 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f16.cuh"
DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_F16);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q4_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q4_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q5_0);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q5_1);

5
ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu Normal file
View file

@ -0,0 +1,5 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-vec-f32.cuh"
DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q8_0);

10
ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb16.cu Normal file
View file

@ -0,0 +1,10 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-wmma-f16.cuh"
DECL_FATTN_WMMA_F16_CASE(64, 16, float);
DECL_FATTN_WMMA_F16_CASE(80, 16, float);
DECL_FATTN_WMMA_F16_CASE(96, 16, float);
DECL_FATTN_WMMA_F16_CASE(112, 16, float);
DECL_FATTN_WMMA_F16_CASE(128, 16, float);
DECL_FATTN_WMMA_F16_CASE(256, 16, float);

9
ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb32.cu Normal file
View file

@ -0,0 +1,9 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-wmma-f16.cuh"
DECL_FATTN_WMMA_F16_CASE(64, 32, float);
DECL_FATTN_WMMA_F16_CASE(80, 32, float);
DECL_FATTN_WMMA_F16_CASE(96, 32, float);
DECL_FATTN_WMMA_F16_CASE(112, 32, float);
DECL_FATTN_WMMA_F16_CASE(128, 32, float);

10
ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb16.cu Normal file
View file

@ -0,0 +1,10 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-wmma-f16.cuh"
DECL_FATTN_WMMA_F16_CASE(64, 16, half);
DECL_FATTN_WMMA_F16_CASE(80, 16, half);
DECL_FATTN_WMMA_F16_CASE(96, 16, half);
DECL_FATTN_WMMA_F16_CASE(112, 16, half);
DECL_FATTN_WMMA_F16_CASE(128, 16, half);
DECL_FATTN_WMMA_F16_CASE(256, 16, half);

10
ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb32.cu Normal file
View file

@ -0,0 +1,10 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-wmma-f16.cuh"
DECL_FATTN_WMMA_F16_CASE(64, 32, half);
DECL_FATTN_WMMA_F16_CASE(80, 32, half);
DECL_FATTN_WMMA_F16_CASE(96, 32, half);
DECL_FATTN_WMMA_F16_CASE(112, 32, half);
DECL_FATTN_WMMA_F16_CASE(128, 32, half);
DECL_FATTN_WMMA_F16_CASE(256, 32, half);

8
ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb8.cu Normal file
View file

@ -0,0 +1,8 @@
// This file has been autogenerated by generate-variants.py, do not edit manually.
#include "../fattn-wmma-f16.cuh"
DECL_FATTN_WMMA_F16_CASE(64, 8, half);
DECL_FATTN_WMMA_F16_CASE(96, 8, half);
DECL_FATTN_WMMA_F16_CASE(128, 8, half);
DECL_FATTN_WMMA_F16_CASE(256, 8, half);