@novastera-oss/llamarn 0.2.6 → 0.2.7

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (192) hide show
  1. package/android/src/main/cpp/include/llama.h +134 -36
  2. package/android/src/main/jniLibs/arm64-v8a/libggml-base.so +0 -0
  3. package/android/src/main/jniLibs/arm64-v8a/libggml-cpu.so +0 -0
  4. package/android/src/main/jniLibs/arm64-v8a/libggml.so +0 -0
  5. package/android/src/main/jniLibs/arm64-v8a/libllama.so +0 -0
  6. package/android/src/main/jniLibs/x86_64/libggml-base.so +0 -0
  7. package/android/src/main/jniLibs/x86_64/libggml-cpu.so +0 -0
  8. package/android/src/main/jniLibs/x86_64/libggml.so +0 -0
  9. package/android/src/main/jniLibs/x86_64/libllama.so +0 -0
  10. package/cpp/LlamaCppModel.cpp +2 -2
  11. package/cpp/LlamaCppModel.h +3 -3
  12. package/cpp/PureCppImpl.cpp +1 -1
  13. package/cpp/PureCppImpl.h +2 -2
  14. package/cpp/build-info.cpp +2 -2
  15. package/cpp/llama.cpp/CMakeLists.txt +15 -4
  16. package/cpp/llama.cpp/Makefile +2 -2
  17. package/cpp/llama.cpp/README.md +32 -13
  18. package/cpp/llama.cpp/common/CMakeLists.txt +10 -20
  19. package/cpp/llama.cpp/common/arg.cpp +30 -6
  20. package/cpp/llama.cpp/common/build-info.cpp.in +2 -2
  21. package/cpp/llama.cpp/common/chat-parser.cpp +5 -0
  22. package/cpp/llama.cpp/common/chat-parser.h +2 -0
  23. package/cpp/llama.cpp/common/chat.cpp +12 -9
  24. package/cpp/llama.cpp/common/chat.h +1 -1
  25. package/cpp/llama.cpp/common/common.cpp +50 -40
  26. package/cpp/llama.cpp/common/common.h +5 -2
  27. package/cpp/llama.cpp/common/speculative.cpp +6 -4
  28. package/cpp/llama.cpp/convert_hf_to_gguf.py +97 -56
  29. package/cpp/llama.cpp/ggml/CMakeLists.txt +47 -2
  30. package/cpp/llama.cpp/ggml/cmake/common.cmake +1 -2
  31. package/cpp/llama.cpp/ggml/src/CMakeLists.txt +47 -13
  32. package/cpp/llama.cpp/ggml/src/ggml-backend-reg.cpp +5 -0
  33. package/cpp/llama.cpp/ggml/src/ggml-cann/common.h +6 -1
  34. package/cpp/llama.cpp/ggml/src/ggml-cann/ggml-cann.cpp +33 -9
  35. package/cpp/llama.cpp/ggml/src/ggml-common.h +4 -0
  36. package/cpp/llama.cpp/ggml/src/ggml-cpu/CMakeLists.txt +93 -24
  37. package/cpp/llama.cpp/ggml/src/ggml-cpu/amx/amx.cpp +1 -1
  38. package/cpp/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp +1 -1
  39. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/arm/cpu-feats.cpp +94 -0
  40. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c +4113 -0
  41. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/arm/repack.cpp +2174 -0
  42. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/loongarch/quants.c +2638 -0
  43. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/powerpc/quants.c +2731 -0
  44. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/riscv/quants.c +2068 -0
  45. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/riscv/repack.cpp +396 -0
  46. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/s390/quants.c +1299 -0
  47. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/wasm/quants.c +1480 -0
  48. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c +4310 -0
  49. package/cpp/llama.cpp/ggml/src/ggml-cpu/{ggml-cpu-aarch64.cpp → arch/x86/repack.cpp} +59 -3206
  50. package/cpp/llama.cpp/ggml/src/ggml-cpu/arch-fallback.h +184 -0
  51. package/cpp/llama.cpp/ggml/src/ggml-cpu/common.h +1 -1
  52. package/cpp/llama.cpp/ggml/src/ggml-cpu/ggml-cpu-impl.h +7 -4
  53. package/cpp/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c +10 -2
  54. package/cpp/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp +8 -8
  55. package/cpp/llama.cpp/ggml/src/ggml-cpu/{ggml-cpu-hbm.cpp → hbm.cpp} +1 -1
  56. package/cpp/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp +1 -1
  57. package/cpp/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp +56 -7
  58. package/cpp/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.h +5 -0
  59. package/cpp/llama.cpp/ggml/src/ggml-cpu/ops.cpp +2 -2
  60. package/cpp/llama.cpp/ggml/src/ggml-cpu/quants.c +1157 -0
  61. package/cpp/llama.cpp/ggml/src/ggml-cpu/{ggml-cpu-quants.h → quants.h} +26 -0
  62. package/cpp/llama.cpp/ggml/src/ggml-cpu/repack.cpp +1555 -0
  63. package/cpp/llama.cpp/ggml/src/ggml-cpu/repack.h +98 -0
  64. package/cpp/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h +2 -4
  65. package/cpp/llama.cpp/ggml/src/ggml-cpu/{ggml-cpu-traits.cpp → traits.cpp} +1 -1
  66. package/cpp/llama.cpp/ggml/src/ggml-cuda/common.cuh +5 -8
  67. package/cpp/llama.cpp/ggml/src/ggml-cuda/fattn-mma-f16.cuh +4 -1
  68. package/cpp/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu +6 -8
  69. package/cpp/llama.cpp/ggml/src/ggml-cuda/ssm-scan.cu +6 -4
  70. package/cpp/llama.cpp/ggml/src/ggml-hip/CMakeLists.txt +4 -0
  71. package/cpp/llama.cpp/ggml/src/ggml-metal/CMakeLists.txt +11 -10
  72. package/cpp/llama.cpp/ggml/src/ggml-metal/ggml-metal.m +33 -8
  73. package/cpp/llama.cpp/ggml/src/ggml-metal/ggml-metal.metal +135 -100
  74. package/cpp/llama.cpp/ggml/src/ggml-opencl/CMakeLists.txt +7 -0
  75. package/cpp/llama.cpp/ggml/src/ggml-opencl/ggml-opencl.cpp +908 -3
  76. package/cpp/llama.cpp/ggml/src/ggml-opencl/kernels/concat.cl +109 -0
  77. package/cpp/llama.cpp/ggml/src/ggml-opencl/kernels/mul_mv_id_q4_0_f32_8x_flat.cl +283 -0
  78. package/cpp/llama.cpp/ggml/src/ggml-opencl/kernels/pad.cl +30 -0
  79. package/cpp/llama.cpp/ggml/src/ggml-opencl/kernels/repeat.cl +39 -0
  80. package/cpp/llama.cpp/ggml/src/ggml-opencl/kernels/tanh.cl +63 -0
  81. package/cpp/llama.cpp/ggml/src/ggml-opencl/kernels/tsembd.cl +48 -0
  82. package/cpp/llama.cpp/ggml/src/ggml-opencl/kernels/upscale.cl +121 -0
  83. package/cpp/llama.cpp/ggml/src/ggml-quants.c +0 -2
  84. package/cpp/llama.cpp/ggml/src/ggml-rpc/ggml-rpc.cpp +18 -15
  85. package/cpp/llama.cpp/ggml/src/ggml-sycl/CMakeLists.txt +1 -1
  86. package/cpp/llama.cpp/ggml/src/ggml-sycl/common.hpp +19 -24
  87. package/cpp/llama.cpp/ggml/src/ggml-sycl/convert.cpp +21 -2
  88. package/cpp/llama.cpp/ggml/src/ggml-sycl/cpy.cpp +121 -4
  89. package/cpp/llama.cpp/ggml/src/ggml-sycl/dequantize.hpp +32 -0
  90. package/cpp/llama.cpp/ggml/src/ggml-sycl/gemm.hpp +3 -0
  91. package/cpp/llama.cpp/ggml/src/ggml-sycl/getrows.cpp +2 -96
  92. package/cpp/llama.cpp/ggml/src/ggml-sycl/ggml-sycl.cpp +164 -38
  93. package/cpp/llama.cpp/ggml/src/ggml-sycl/mmvq.cpp +32 -8
  94. package/cpp/llama.cpp/ggml/src/ggml-sycl/quants.hpp +38 -10
  95. package/cpp/llama.cpp/ggml/src/ggml-sycl/vecdotq.hpp +108 -16
  96. package/cpp/llama.cpp/ggml/src/ggml-vulkan/CMakeLists.txt +26 -29
  97. package/cpp/llama.cpp/ggml/src/ggml-vulkan/ggml-vulkan.cpp +431 -247
  98. package/cpp/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt +0 -12
  99. package/cpp/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/conv_transpose_1d.comp +98 -0
  100. package/cpp/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp +2 -0
  101. package/cpp/llama.cpp/ggml/src/ggml.c +0 -6
  102. package/cpp/llama.cpp/gguf-py/gguf/constants.py +57 -0
  103. package/cpp/llama.cpp/gguf-py/gguf/gguf_writer.py +4 -1
  104. package/cpp/llama.cpp/gguf-py/gguf/tensor_mapping.py +14 -3
  105. package/cpp/llama.cpp/include/llama.h +134 -36
  106. package/cpp/llama.cpp/requirements/requirements-compare-llama-bench.txt +1 -0
  107. package/cpp/llama.cpp/src/CMakeLists.txt +2 -2
  108. package/cpp/llama.cpp/src/llama-arch.cpp +95 -3
  109. package/cpp/llama.cpp/src/llama-arch.h +7 -1
  110. package/cpp/llama.cpp/src/llama-batch.cpp +270 -19
  111. package/cpp/llama.cpp/src/llama-batch.h +36 -11
  112. package/cpp/llama.cpp/src/llama-chat.cpp +19 -2
  113. package/cpp/llama.cpp/src/llama-chat.h +1 -0
  114. package/cpp/llama.cpp/src/llama-context.cpp +313 -213
  115. package/cpp/llama.cpp/src/llama-context.h +16 -12
  116. package/cpp/llama.cpp/src/llama-cparams.cpp +1 -1
  117. package/cpp/llama.cpp/src/llama-cparams.h +1 -1
  118. package/cpp/llama.cpp/src/llama-graph.cpp +249 -129
  119. package/cpp/llama.cpp/src/llama-graph.h +90 -34
  120. package/cpp/llama.cpp/src/llama-hparams.cpp +6 -2
  121. package/cpp/llama.cpp/src/llama-hparams.h +8 -2
  122. package/cpp/llama.cpp/src/llama-kv-cache-unified-iswa.cpp +82 -50
  123. package/cpp/llama.cpp/src/llama-kv-cache-unified-iswa.h +23 -26
  124. package/cpp/llama.cpp/src/llama-kv-cache-unified.cpp +292 -174
  125. package/cpp/llama.cpp/src/llama-kv-cache-unified.h +68 -38
  126. package/cpp/llama.cpp/src/llama-kv-cells.h +18 -13
  127. package/cpp/llama.cpp/src/llama-memory-hybrid.cpp +247 -0
  128. package/cpp/llama.cpp/src/llama-memory-hybrid.h +143 -0
  129. package/cpp/llama.cpp/src/{llama-kv-cache-recurrent.cpp → llama-memory-recurrent.cpp} +266 -282
  130. package/cpp/llama.cpp/src/{llama-kv-cache-recurrent.h → llama-memory-recurrent.h} +54 -57
  131. package/cpp/llama.cpp/src/llama-memory.cpp +41 -0
  132. package/cpp/llama.cpp/src/llama-memory.h +64 -23
  133. package/cpp/llama.cpp/src/llama-mmap.cpp +1 -1
  134. package/cpp/llama.cpp/src/llama-model-loader.cpp +42 -17
  135. package/cpp/llama.cpp/src/llama-model.cpp +726 -141
  136. package/cpp/llama.cpp/src/llama-model.h +4 -0
  137. package/cpp/llama.cpp/src/llama-quant.cpp +2 -1
  138. package/cpp/llama.cpp/src/llama-vocab.cpp +32 -23
  139. package/cpp/llama.cpp/src/llama.cpp +11 -7
  140. package/cpp/llama.cpp/src/unicode.cpp +5 -0
  141. package/cpp/rn-completion.cpp +2 -2
  142. package/cpp/{rn-llama.hpp → rn-llama.h} +1 -1
  143. package/ios/include/chat.h +1 -1
  144. package/ios/include/common.h +5 -2
  145. package/ios/include/llama.h +134 -36
  146. package/ios/libs/llama.xcframework/Info.plist +18 -18
  147. package/ios/libs/llama.xcframework/ios-arm64/dSYMs/llama.dSYM/Contents/Resources/DWARF/llama +0 -0
  148. package/ios/libs/llama.xcframework/ios-arm64/dSYMs/llama.dSYM/Contents/Resources/Relocations/aarch64/llama.yml +4863 -4689
  149. package/ios/libs/llama.xcframework/ios-arm64/llama.framework/Headers/llama.h +134 -36
  150. package/ios/libs/llama.xcframework/ios-arm64/llama.framework/llama +0 -0
  151. package/ios/libs/llama.xcframework/ios-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/DWARF/llama +0 -0
  152. package/ios/libs/llama.xcframework/ios-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/Relocations/aarch64/llama.yml +4834 -4710
  153. package/ios/libs/llama.xcframework/ios-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/Relocations/x86_64/llama.yml +3742 -3622
  154. package/ios/libs/llama.xcframework/ios-arm64_x86_64-simulator/llama.framework/Headers/llama.h +134 -36
  155. package/ios/libs/llama.xcframework/ios-arm64_x86_64-simulator/llama.framework/llama +0 -0
  156. package/ios/libs/llama.xcframework/macos-arm64_x86_64/dSYMs/llama.dSYM/Contents/Resources/DWARF/llama +0 -0
  157. package/ios/libs/llama.xcframework/macos-arm64_x86_64/dSYMs/llama.dSYM/Contents/Resources/Relocations/aarch64/llama.yml +4834 -4710
  158. package/ios/libs/llama.xcframework/macos-arm64_x86_64/dSYMs/llama.dSYM/Contents/Resources/Relocations/x86_64/llama.yml +3744 -3624
  159. package/ios/libs/llama.xcframework/macos-arm64_x86_64/llama.framework/Headers/llama.h +134 -36
  160. package/ios/libs/llama.xcframework/macos-arm64_x86_64/llama.framework/Versions/A/Headers/llama.h +134 -36
  161. package/ios/libs/llama.xcframework/macos-arm64_x86_64/llama.framework/Versions/A/llama +0 -0
  162. package/ios/libs/llama.xcframework/macos-arm64_x86_64/llama.framework/Versions/Current/Headers/llama.h +134 -36
  163. package/ios/libs/llama.xcframework/macos-arm64_x86_64/llama.framework/Versions/Current/llama +0 -0
  164. package/ios/libs/llama.xcframework/macos-arm64_x86_64/llama.framework/llama +0 -0
  165. package/ios/libs/llama.xcframework/tvos-arm64/dSYMs/llama.dSYM/Contents/Resources/DWARF/llama +0 -0
  166. package/ios/libs/llama.xcframework/tvos-arm64/dSYMs/llama.dSYM/Contents/Resources/Relocations/aarch64/llama.yml +4863 -4689
  167. package/ios/libs/llama.xcframework/tvos-arm64/llama.framework/Headers/llama.h +134 -36
  168. package/ios/libs/llama.xcframework/tvos-arm64/llama.framework/llama +0 -0
  169. package/ios/libs/llama.xcframework/tvos-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/DWARF/llama +0 -0
  170. package/ios/libs/llama.xcframework/tvos-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/Relocations/aarch64/llama.yml +4834 -4710
  171. package/ios/libs/llama.xcframework/tvos-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/Relocations/x86_64/llama.yml +3742 -3622
  172. package/ios/libs/llama.xcframework/tvos-arm64_x86_64-simulator/llama.framework/Headers/llama.h +134 -36
  173. package/ios/libs/llama.xcframework/tvos-arm64_x86_64-simulator/llama.framework/llama +0 -0
  174. package/ios/libs/llama.xcframework/xros-arm64/dSYMs/llama.dSYM/Contents/Resources/DWARF/llama +0 -0
  175. package/ios/libs/llama.xcframework/xros-arm64/dSYMs/llama.dSYM/Contents/Resources/Relocations/aarch64/llama.yml +4900 -4725
  176. package/ios/libs/llama.xcframework/xros-arm64/llama.framework/Headers/llama.h +134 -36
  177. package/ios/libs/llama.xcframework/xros-arm64/llama.framework/llama +0 -0
  178. package/ios/libs/llama.xcframework/xros-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/DWARF/llama +0 -0
  179. package/ios/libs/llama.xcframework/xros-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/Relocations/aarch64/llama.yml +4871 -4746
  180. package/ios/libs/llama.xcframework/xros-arm64_x86_64-simulator/dSYMs/llama.dSYM/Contents/Resources/Relocations/x86_64/llama.yml +3773 -3652
  181. package/ios/libs/llama.xcframework/xros-arm64_x86_64-simulator/llama.framework/Headers/llama.h +134 -36
  182. package/ios/libs/llama.xcframework/xros-arm64_x86_64-simulator/llama.framework/llama +0 -0
  183. package/package.json +1 -2
  184. package/cpp/llama.cpp/common/cmake/build-info-gen-cpp.cmake +0 -24
  185. package/cpp/llama.cpp/ggml/src/ggml-cpu/ggml-cpu-aarch64.h +0 -8
  186. package/cpp/llama.cpp/ggml/src/ggml-cpu/ggml-cpu-quants.c +0 -13891
  187. package/cpp/llama.cpp/src/llama-kv-cache.cpp +0 -1
  188. package/cpp/llama.cpp/src/llama-kv-cache.h +0 -44
  189. /package/cpp/llama.cpp/ggml/src/ggml-cpu/{cpu-feats-x86.cpp → arch/x86/cpu-feats.cpp} +0 -0
  190. /package/cpp/llama.cpp/ggml/src/ggml-cpu/{ggml-cpu-hbm.h → hbm.h} +0 -0
  191. /package/cpp/llama.cpp/ggml/src/ggml-cpu/{ggml-cpu-traits.h → traits.h} +0 -0
  192. /package/cpp/{rn-utils.hpp → rn-utils.h} +0 -0
package/cpp/llama.cpp/ggml/src/ggml-cpu/{ggml-cpu-quants.h → quants.h} RENAMED
@@ -58,6 +58,32 @@ void ggml_vec_dot_iq4_nl_q8_0 (int n, float * GGML_RESTRICT s, size_t bs, const
58
58
  void ggml_vec_dot_iq4_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
59
59
  void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
60
60
 
61
+ // Generic implementation
62
+ void quantize_row_q8_0_generic(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
63
+ void quantize_row_q8_1_generic(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
64
+ void quantize_row_q8_K_generic(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
65
+ void ggml_vec_dot_q4_0_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
66
+ void ggml_vec_dot_q4_1_q8_1_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
67
+ void ggml_vec_dot_q5_0_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
68
+ void ggml_vec_dot_q5_1_q8_1_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
69
+ void ggml_vec_dot_q8_0_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
70
+ void ggml_vec_dot_tq1_0_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
71
+ void ggml_vec_dot_tq2_0_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
72
+ void ggml_vec_dot_q2_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
73
+ void ggml_vec_dot_q3_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
74
+ void ggml_vec_dot_q4_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
75
+ void ggml_vec_dot_q5_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
76
+ void ggml_vec_dot_q6_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
77
+ void ggml_vec_dot_iq2_xxs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
78
+ void ggml_vec_dot_iq2_xs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
79
+ void ggml_vec_dot_iq2_s_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
80
+ void ggml_vec_dot_iq3_xxs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
81
+ void ggml_vec_dot_iq3_s_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
82
+ void ggml_vec_dot_iq1_s_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
83
+ void ggml_vec_dot_iq1_m_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
84
+ void ggml_vec_dot_iq4_nl_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
85
+ void ggml_vec_dot_iq4_xs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
86
+
61
87
  #ifdef __cplusplus
62
88
  }
63
89
  #endif