llama_cpp 0.16.0 → 0.16.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (134) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +6 -0
  3. data/ext/llama_cpp/extconf.rb +2 -0
  4. data/ext/llama_cpp/llama_cpp.cpp +2 -0
  5. data/lib/llama_cpp/version.rb +2 -2
  6. data/sig/llama_cpp.rbs +2 -0
  7. data/vendor/tmp/llama.cpp/Makefile +110 -53
  8. data/vendor/tmp/llama.cpp/ggml-alloc.c +78 -22
  9. data/vendor/tmp/llama.cpp/ggml-backend-impl.h +20 -8
  10. data/vendor/tmp/llama.cpp/ggml-backend.c +178 -64
  11. data/vendor/tmp/llama.cpp/ggml-backend.h +3 -3
  12. data/vendor/tmp/llama.cpp/ggml-blas.cpp +363 -0
  13. data/vendor/tmp/llama.cpp/ggml-blas.h +23 -0
  14. data/vendor/tmp/llama.cpp/ggml-common.h +6 -0
  15. data/vendor/tmp/llama.cpp/ggml-cuda/argsort.cu +1 -0
  16. data/vendor/tmp/llama.cpp/ggml-cuda/dmmv.cu +21 -9
  17. data/vendor/tmp/llama.cpp/ggml-cuda/fattn-tile-f16.cu +1 -1
  18. data/vendor/tmp/llama.cpp/ggml-cuda/mmq.cu +15 -1491
  19. data/vendor/tmp/llama.cpp/ggml-cuda/mmvq.cu +76 -61
  20. data/vendor/tmp/llama.cpp/ggml-cuda/quantize.cu +77 -10
  21. data/vendor/tmp/llama.cpp/ggml-cuda/softmax.cu +1 -0
  22. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu +1 -1
  23. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu +1 -1
  24. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu +1 -1
  25. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu +1 -1
  26. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu +1 -1
  27. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu +1 -1
  28. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu +1 -1
  29. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu +1 -1
  30. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu +1 -1
  31. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu +1 -1
  32. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu +1 -1
  33. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu +1 -1
  34. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu +1 -1
  35. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu +1 -1
  36. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu +1 -1
  37. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu +1 -1
  38. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_1.cu +1 -1
  39. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q8_0.cu +1 -1
  40. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-f16.cu +1 -1
  41. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_0.cu +1 -1
  42. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_1.cu +1 -1
  43. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_0.cu +1 -1
  44. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_1.cu +1 -1
  45. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q8_0.cu +1 -1
  46. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-f16.cu +1 -1
  47. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_0.cu +1 -1
  48. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_1.cu +1 -1
  49. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_0.cu +1 -1
  50. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu +1 -1
  51. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu +1 -1
  52. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu +1 -1
  53. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu +1 -1
  54. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu +1 -1
  55. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu +1 -1
  56. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu +1 -1
  57. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu +1 -1
  58. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu +1 -1
  59. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu +1 -1
  60. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu +1 -1
  61. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu +1 -1
  62. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu +1 -1
  63. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu +1 -1
  64. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu +1 -1
  65. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu +1 -1
  66. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu +1 -1
  67. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu +1 -1
  68. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu +1 -1
  69. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu +1 -1
  70. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu +1 -1
  71. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu +1 -1
  72. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu +1 -1
  73. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu +1 -1
  74. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu +1 -1
  75. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu +1 -1
  76. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu +1 -1
  77. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu +1 -1
  78. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu +1 -1
  79. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu +1 -1
  80. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu +1 -1
  81. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu +1 -1
  82. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu +1 -1
  83. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu +1 -1
  84. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu +1 -1
  85. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu +1 -1
  86. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu +1 -1
  87. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu +1 -1
  88. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu +1 -1
  89. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu +1 -1
  90. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu +1 -1
  91. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu +1 -1
  92. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu +1 -1
  93. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu +1 -1
  94. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu +1 -1
  95. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu +1 -1
  96. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu +1 -1
  97. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu +1 -1
  98. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu +1 -1
  99. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu +1 -1
  100. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu +1 -1
  101. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu +1 -1
  102. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu +1 -1
  103. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu +1 -1
  104. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu +1 -1
  105. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu +1 -1
  106. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu +1 -1
  107. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu +1 -1
  108. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb16.cu +1 -1
  109. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb32.cu +1 -1
  110. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb16.cu +1 -1
  111. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb32.cu +1 -1
  112. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb8.cu +1 -1
  113. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q2_k.cu +5 -0
  114. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q3_k.cu +5 -0
  115. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q4_0.cu +5 -0
  116. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q4_1.cu +5 -0
  117. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q4_k.cu +5 -0
  118. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q5_0.cu +5 -0
  119. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q5_1.cu +5 -0
  120. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q5_k.cu +5 -0
  121. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q6_k.cu +5 -0
  122. data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q8_0.cu +5 -0
  123. data/vendor/tmp/llama.cpp/ggml-cuda/unary.cu +20 -0
  124. data/vendor/tmp/llama.cpp/ggml-cuda.cu +95 -129
  125. data/vendor/tmp/llama.cpp/ggml-kompute.cpp +8 -7
  126. data/vendor/tmp/llama.cpp/ggml-metal.m +11 -9
  127. data/vendor/tmp/llama.cpp/ggml-rpc.cpp +13 -12
  128. data/vendor/tmp/llama.cpp/ggml-sycl.cpp +19 -23
  129. data/vendor/tmp/llama.cpp/ggml-vulkan-shaders.hpp +1230 -1129
  130. data/vendor/tmp/llama.cpp/ggml-vulkan.cpp +181 -148
  131. data/vendor/tmp/llama.cpp/ggml.c +102 -275
  132. data/vendor/tmp/llama.cpp/llama.cpp +103 -47
  133. data/vendor/tmp/llama.cpp/llama.h +4 -0
  134. metadata +15 -3
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-vec-f32.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-wmma-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb32.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-wmma-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb16.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-wmma-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb32.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-wmma-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb8.cu CHANGED
@@ -1,4 +1,4 @@
1
- // This file has been autogenerated by generate-variants.py, do not edit manually.
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
2
 
3
3
  #include "../fattn-wmma-f16.cuh"
4
4
 
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q2_k.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q2_K);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q3_k.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q3_K);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q4_0.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q4_0);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q4_1.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q4_1);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q4_k.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q4_K);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q5_0.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q5_0);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q5_1.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q5_1);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q5_k.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q5_K);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q6_k.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q6_K);
data/vendor/tmp/llama.cpp/ggml-cuda/template-instances/mmq-instance-q8_0.cu ADDED
@@ -0,0 +1,5 @@
1
+ // This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
+
3
+ #include "../mmq.cuh"
4
+
5
+ DECL_MMQ_CASE(GGML_TYPE_Q8_0);