llama-cpp-pydist 0.14.0__py3-none-any.whl → 0.16.0__py3-none-any.whl

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 (369) hide show
  1. llama_cpp/binaries/{llama-b6957-bin-win-cpu-x64.zip → llama-b7213-bin-win-cpu-x64.zip} +0 -0
  2. {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/METADATA +189 -1
  3. {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/RECORD +362 -296
  4. vendor_llama_cpp_pydist/llama.cpp/.devops/cann.Dockerfile +6 -7
  5. vendor_llama_cpp_pydist/llama.cpp/.devops/cpu.Dockerfile +1 -1
  6. vendor_llama_cpp_pydist/llama.cpp/.devops/cuda.Dockerfile +1 -1
  7. vendor_llama_cpp_pydist/llama.cpp/.devops/intel.Dockerfile +1 -1
  8. vendor_llama_cpp_pydist/llama.cpp/.devops/musa.Dockerfile +1 -1
  9. vendor_llama_cpp_pydist/llama.cpp/.devops/nix/package.nix +2 -0
  10. vendor_llama_cpp_pydist/llama.cpp/.devops/rocm.Dockerfile +1 -1
  11. vendor_llama_cpp_pydist/llama.cpp/.devops/vulkan.Dockerfile +6 -23
  12. vendor_llama_cpp_pydist/llama.cpp/.editorconfig +8 -0
  13. vendor_llama_cpp_pydist/llama.cpp/.github/copilot-instructions.md +1 -1
  14. vendor_llama_cpp_pydist/llama.cpp/.github/workflows/build.yml +142 -102
  15. vendor_llama_cpp_pydist/llama.cpp/.github/workflows/check-vendor.yml +52 -0
  16. vendor_llama_cpp_pydist/llama.cpp/.github/workflows/release.yml +46 -0
  17. vendor_llama_cpp_pydist/llama.cpp/.github/workflows/server.yml +10 -17
  18. vendor_llama_cpp_pydist/llama.cpp/.gitignore +45 -63
  19. vendor_llama_cpp_pydist/llama.cpp/CMakeLists.txt +4 -0
  20. vendor_llama_cpp_pydist/llama.cpp/CODEOWNERS +8 -23
  21. vendor_llama_cpp_pydist/llama.cpp/CONTRIBUTING.md +1 -0
  22. vendor_llama_cpp_pydist/llama.cpp/README.md +2 -0
  23. vendor_llama_cpp_pydist/llama.cpp/SECURITY.md +2 -0
  24. vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547.html +35144 -0
  25. vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547.json +6 -0
  26. vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547_allresults.json +2896 -0
  27. vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/dgx-spark.md +264 -0
  28. vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/run-aime-120b-t8-x8-high.log +11 -0
  29. vendor_llama_cpp_pydist/llama.cpp/build-xcframework.sh +4 -0
  30. vendor_llama_cpp_pydist/llama.cpp/ci/run.sh +14 -9
  31. vendor_llama_cpp_pydist/llama.cpp/common/CMakeLists.txt +10 -37
  32. vendor_llama_cpp_pydist/llama.cpp/common/arg.cpp +63 -1001
  33. vendor_llama_cpp_pydist/llama.cpp/common/arg.h +2 -2
  34. vendor_llama_cpp_pydist/llama.cpp/common/chat-parser-xml-toolcall.cpp +861 -0
  35. vendor_llama_cpp_pydist/llama.cpp/common/chat-parser-xml-toolcall.h +45 -0
  36. vendor_llama_cpp_pydist/llama.cpp/common/chat-parser.cpp +968 -0
  37. vendor_llama_cpp_pydist/llama.cpp/common/chat-parser.h +10 -0
  38. vendor_llama_cpp_pydist/llama.cpp/common/chat.cpp +311 -889
  39. vendor_llama_cpp_pydist/llama.cpp/common/chat.h +6 -0
  40. vendor_llama_cpp_pydist/llama.cpp/common/common.cpp +97 -6
  41. vendor_llama_cpp_pydist/llama.cpp/common/common.h +40 -7
  42. vendor_llama_cpp_pydist/llama.cpp/common/download.cpp +1079 -0
  43. vendor_llama_cpp_pydist/llama.cpp/common/download.h +55 -0
  44. vendor_llama_cpp_pydist/llama.cpp/common/json-partial.cpp +19 -2
  45. vendor_llama_cpp_pydist/llama.cpp/common/json-schema-to-grammar.cpp +4 -2
  46. vendor_llama_cpp_pydist/llama.cpp/common/json-schema-to-grammar.h +2 -0
  47. vendor_llama_cpp_pydist/llama.cpp/common/log.cpp +20 -0
  48. vendor_llama_cpp_pydist/llama.cpp/common/log.h +21 -12
  49. vendor_llama_cpp_pydist/llama.cpp/common/sampling.cpp +60 -6
  50. vendor_llama_cpp_pydist/llama.cpp/convert_hf_to_gguf.py +366 -130
  51. vendor_llama_cpp_pydist/llama.cpp/convert_hf_to_gguf_update.py +1 -0
  52. vendor_llama_cpp_pydist/llama.cpp/convert_lora_to_gguf.py +11 -5
  53. vendor_llama_cpp_pydist/llama.cpp/docs/backend/CANN.md +6 -1
  54. vendor_llama_cpp_pydist/llama.cpp/docs/backend/SYCL.md +13 -0
  55. vendor_llama_cpp_pydist/llama.cpp/docs/build.md +42 -0
  56. vendor_llama_cpp_pydist/llama.cpp/docs/ops/CPU.csv +16067 -5133
  57. vendor_llama_cpp_pydist/llama.cpp/docs/ops/CUDA.csv +16224 -6894
  58. vendor_llama_cpp_pydist/llama.cpp/docs/ops/SYCL.csv +4744 -2430
  59. vendor_llama_cpp_pydist/llama.cpp/docs/ops/Vulkan.csv +14542 -4366
  60. vendor_llama_cpp_pydist/llama.cpp/docs/ops.md +58 -53
  61. vendor_llama_cpp_pydist/llama.cpp/ggml/CMakeLists.txt +7 -5
  62. vendor_llama_cpp_pydist/llama.cpp/ggml/include/ggml-rpc.h +1 -1
  63. vendor_llama_cpp_pydist/llama.cpp/ggml/include/ggml.h +85 -5
  64. vendor_llama_cpp_pydist/llama.cpp/ggml/src/CMakeLists.txt +38 -0
  65. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-alloc.c +8 -3
  66. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-backend.cpp +38 -5
  67. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/acl_tensor.cpp +19 -10
  68. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/acl_tensor.h +99 -19
  69. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/aclnn_ops.cpp +1015 -755
  70. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/aclnn_ops.h +121 -194
  71. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/common.h +89 -158
  72. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/ggml-cann.cpp +53 -33
  73. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/CMakeLists.txt +91 -61
  74. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c +428 -26
  75. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/arm/repack.cpp +721 -0
  76. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/riscv/cpu-feats.cpp +38 -0
  77. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/riscv/quants.c +108 -49
  78. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp +6 -6
  79. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch-fallback.h +22 -2
  80. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c +59 -16
  81. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/kleidiai/kernels.cpp +296 -3
  82. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/kleidiai/kernels.h +1 -0
  83. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp +235 -34
  84. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/ops.cpp +414 -317
  85. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/ops.h +5 -4
  86. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/repack.cpp +336 -44
  87. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/repack.h +6 -0
  88. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h +16 -14
  89. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/unary-ops.cpp +16 -0
  90. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/unary-ops.h +2 -0
  91. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/vec.cpp +17 -0
  92. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/vec.h +143 -133
  93. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/CMakeLists.txt +1 -0
  94. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/argsort.cu +1 -1
  95. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/common.cuh +194 -18
  96. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/convert.cuh +9 -0
  97. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/cpy-utils.cuh +1 -1
  98. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/cpy.cu +174 -45
  99. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn-common.cuh +2 -2
  100. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn-tile.cuh +1 -1
  101. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn-vec.cuh +18 -18
  102. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu +502 -44
  103. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mma.cuh +190 -3
  104. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmf.cu +17 -5
  105. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmf.cuh +54 -21
  106. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmq.cu +7 -1
  107. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmq.cuh +302 -139
  108. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmvf.cu +14 -1
  109. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmvf.cuh +1 -1
  110. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/rope.cu +162 -60
  111. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/rope.cuh +2 -0
  112. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/solve_tri.cu +203 -0
  113. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/solve_tri.cuh +3 -0
  114. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/unary.cu +16 -0
  115. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/unary.cuh +4 -0
  116. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/upscale.cu +163 -7
  117. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/vendors/hip.h +1 -1
  118. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/CMakeLists.txt +10 -0
  119. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/ggml-hexagon.cpp +133 -395
  120. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/act-ops.c +12 -18
  121. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/binary-ops.c +46 -30
  122. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/htp-dma.h +7 -0
  123. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/htp-msg.h +4 -4
  124. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/htp-ops.h +11 -0
  125. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/hvx-exp.c +20 -6
  126. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/hvx-inverse.c +15 -3
  127. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/hvx-utils.c +20 -7
  128. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/hvx-utils.h +56 -11
  129. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/main.c +12 -3
  130. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/ops-utils.h +33 -0
  131. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/rope-ops.c +80 -7
  132. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp-utils.c +6 -0
  133. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp-utils.h +1 -0
  134. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-impl.h +1 -1
  135. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-context.m +5 -6
  136. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-device.cpp +148 -0
  137. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-device.h +10 -1
  138. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-device.m +217 -10
  139. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-impl.h +99 -2
  140. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-ops.cpp +472 -85
  141. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-ops.h +3 -0
  142. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal.cpp +9 -0
  143. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal.metal +822 -152
  144. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/CMakeLists.txt +5 -0
  145. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/ggml-opencl.cpp +558 -5
  146. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/mean.cl +39 -0
  147. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/mul_mm_f16_f32_kq_kqv.cl +273 -0
  148. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/rms_norm.cl +25 -10
  149. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/set_rows.cl +35 -16
  150. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/sqr.cl +53 -0
  151. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/sqrt.cl +53 -0
  152. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/ssm_conv.cl +77 -0
  153. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-rpc/ggml-rpc.cpp +91 -20
  154. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/CMakeLists.txt +6 -2
  155. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/common.hpp +26 -0
  156. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/concat.cpp +55 -44
  157. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/cpy.cpp +0 -3
  158. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/element_wise.cpp +112 -250
  159. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/ggml-sycl.cpp +9 -11
  160. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/pad_reflect_1d.cpp +87 -59
  161. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/pad_reflect_1d.hpp +2 -0
  162. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/ggml-vulkan.cpp +2326 -1849
  163. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/abs.comp +21 -0
  164. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/add1.comp +28 -0
  165. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/arange.comp +20 -0
  166. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/argsort.comp +20 -21
  167. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/argsort_large.comp +114 -0
  168. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/ceil.comp +22 -0
  169. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/conv2d_mm.comp +39 -36
  170. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/copy_transpose.comp +67 -0
  171. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/cumsum.comp +69 -0
  172. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl +0 -7
  173. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/fill.comp +19 -0
  174. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/flash_attn.comp +33 -15
  175. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp +34 -1
  176. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp +37 -19
  177. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/floor.comp +22 -0
  178. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/generic_binary_head.glsl +15 -0
  179. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/generic_unary_head.glsl +7 -0
  180. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/log.comp +18 -0
  181. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec.comp +1 -0
  182. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_base.glsl +53 -38
  183. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iface.glsl +35 -0
  184. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_nc.comp +8 -12
  185. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_p021.comp +8 -12
  186. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vecq.comp +27 -35
  187. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vecq_funcs.glsl +379 -0
  188. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mm.comp +31 -2
  189. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp +4 -4
  190. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_funcs.glsl +62 -185
  191. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/neg.comp +20 -0
  192. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/quantize_q8_1.comp +1 -1
  193. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rms_norm.comp +43 -1
  194. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_funcs.glsl +227 -0
  195. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_head.glsl +9 -47
  196. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp +4 -63
  197. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_neox.comp +4 -41
  198. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_norm.comp +4 -41
  199. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_params.glsl +27 -0
  200. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_vision.comp +4 -40
  201. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/round.comp +29 -0
  202. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/softplus.comp +23 -0
  203. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/solve_tri.comp +72 -0
  204. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/step.comp +22 -0
  205. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/sum_rows.comp +1 -24
  206. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/sum_rows.glsl +25 -0
  207. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/topk_argsort.comp +113 -0
  208. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/topk_nary_search.comp +199 -0
  209. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/tri.comp +43 -0
  210. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/trunc.comp +22 -0
  211. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/upscale.comp +37 -0
  212. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp +110 -34
  213. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/ggml-webgpu.cpp +313 -13
  214. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py +6 -3
  215. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat.tmpl.wgsl +5 -5
  216. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl +97 -0
  217. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.tmpl.wgsl +247 -0
  218. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_subgroup_matrix.tmpl.wgsl +302 -0
  219. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.tmpl.wgsl +267 -0
  220. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml.c +199 -29
  221. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/constants.py +120 -0
  222. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/gguf_writer.py +56 -6
  223. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/lazy.py +8 -3
  224. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/metadata.py +85 -0
  225. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/scripts/gguf_convert_endian.py +12 -18
  226. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/scripts/gguf_editor_gui.py +1 -1
  227. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/scripts/gguf_new_metadata.py +1 -1
  228. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/tensor_mapping.py +24 -7
  229. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/utility.py +80 -0
  230. vendor_llama_cpp_pydist/llama.cpp/include/llama.h +20 -0
  231. vendor_llama_cpp_pydist/llama.cpp/scripts/sync-ggml.last +1 -1
  232. vendor_llama_cpp_pydist/llama.cpp/scripts/sync_vendor.py +21 -2
  233. vendor_llama_cpp_pydist/llama.cpp/src/CMakeLists.txt +9 -0
  234. vendor_llama_cpp_pydist/llama.cpp/src/llama-arch.cpp +155 -16
  235. vendor_llama_cpp_pydist/llama.cpp/src/llama-arch.h +19 -0
  236. vendor_llama_cpp_pydist/llama.cpp/src/llama-context.cpp +16 -6
  237. vendor_llama_cpp_pydist/llama.cpp/src/llama-grammar.cpp +17 -9
  238. vendor_llama_cpp_pydist/llama.cpp/src/llama-graph.cpp +10 -12
  239. vendor_llama_cpp_pydist/llama.cpp/src/llama-hparams.cpp +10 -0
  240. vendor_llama_cpp_pydist/llama.cpp/src/llama-hparams.h +6 -3
  241. vendor_llama_cpp_pydist/llama.cpp/src/llama-impl.cpp +3 -3
  242. vendor_llama_cpp_pydist/llama.cpp/src/llama-kv-cache-iswa.cpp +3 -1
  243. vendor_llama_cpp_pydist/llama.cpp/src/llama-memory-recurrent.cpp +4 -3
  244. vendor_llama_cpp_pydist/llama.cpp/src/llama-model.cpp +300 -28
  245. vendor_llama_cpp_pydist/llama.cpp/src/llama-model.h +6 -0
  246. vendor_llama_cpp_pydist/llama.cpp/src/llama-quant.cpp +13 -5
  247. vendor_llama_cpp_pydist/llama.cpp/src/llama-sampling.cpp +13 -11
  248. vendor_llama_cpp_pydist/llama.cpp/src/llama-vocab.cpp +17 -1
  249. vendor_llama_cpp_pydist/llama.cpp/src/llama-vocab.h +1 -0
  250. vendor_llama_cpp_pydist/llama.cpp/src/models/afmoe.cpp +187 -0
  251. vendor_llama_cpp_pydist/llama.cpp/src/models/deepseek2.cpp +2 -1
  252. vendor_llama_cpp_pydist/llama.cpp/src/models/ernie4-5.cpp +4 -5
  253. vendor_llama_cpp_pydist/llama.cpp/src/models/lfm2.cpp +5 -3
  254. vendor_llama_cpp_pydist/llama.cpp/src/models/mistral3.cpp +160 -0
  255. vendor_llama_cpp_pydist/llama.cpp/src/models/models.h +63 -1
  256. vendor_llama_cpp_pydist/llama.cpp/src/models/openai-moe-iswa.cpp +2 -1
  257. vendor_llama_cpp_pydist/llama.cpp/src/models/qwen3next.cpp +1042 -0
  258. vendor_llama_cpp_pydist/llama.cpp/src/models/qwen3vl-moe.cpp +1 -2
  259. vendor_llama_cpp_pydist/llama.cpp/src/models/qwen3vl.cpp +1 -4
  260. vendor_llama_cpp_pydist/llama.cpp/src/models/rnd1.cpp +126 -0
  261. vendor_llama_cpp_pydist/llama.cpp/src/unicode.cpp +77 -0
  262. vendor_llama_cpp_pydist/llama.cpp/tests/CMakeLists.txt +1 -1
  263. vendor_llama_cpp_pydist/llama.cpp/tests/test-backend-ops.cpp +742 -178
  264. vendor_llama_cpp_pydist/llama.cpp/tests/test-chat.cpp +1033 -19
  265. vendor_llama_cpp_pydist/llama.cpp/tests/test-json-schema-to-grammar.cpp +26 -0
  266. vendor_llama_cpp_pydist/llama.cpp/tests/test-rope.cpp +6 -5
  267. vendor_llama_cpp_pydist/llama.cpp/tools/batched-bench/batched-bench.cpp +31 -11
  268. vendor_llama_cpp_pydist/llama.cpp/tools/llama-bench/llama-bench.cpp +40 -7
  269. vendor_llama_cpp_pydist/llama.cpp/tools/main/main.cpp +17 -3
  270. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/CMakeLists.txt +5 -0
  271. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip-impl.h +5 -12
  272. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip.cpp +100 -143
  273. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip.h +0 -1
  274. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd-cli.cpp +2 -2
  275. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd-helper.cpp +61 -4
  276. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd-helper.h +5 -0
  277. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd.cpp +10 -3
  278. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd.h +4 -1
  279. vendor_llama_cpp_pydist/llama.cpp/tools/rpc/CMakeLists.txt +4 -0
  280. vendor_llama_cpp_pydist/llama.cpp/tools/server/CMakeLists.txt +15 -2
  281. vendor_llama_cpp_pydist/llama.cpp/tools/server/README.md +101 -20
  282. vendor_llama_cpp_pydist/llama.cpp/tools/server/public/index.html.gz +0 -0
  283. vendor_llama_cpp_pydist/llama.cpp/tools/server/public_legacy/json-schema-to-grammar.mjs +2 -2
  284. vendor_llama_cpp_pydist/llama.cpp/tools/server/{utils.hpp → server-common.cpp} +998 -907
  285. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-common.h +355 -0
  286. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-context.cpp +3619 -0
  287. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-context.h +83 -0
  288. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-http.cpp +394 -0
  289. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-http.h +78 -0
  290. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-queue.cpp +351 -0
  291. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-queue.h +146 -0
  292. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-task.cpp +1474 -0
  293. vendor_llama_cpp_pydist/llama.cpp/tools/server/server-task.h +460 -0
  294. vendor_llama_cpp_pydist/llama.cpp/tools/server/server.cpp +123 -5685
  295. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/conftest.py +6 -0
  296. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_basic.py +0 -6
  297. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_compat_anthropic.py +807 -0
  298. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_completion.py +42 -0
  299. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_security.py +13 -0
  300. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_speculative.py +6 -6
  301. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/utils.py +2 -0
  302. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/.gitignore +1 -0
  303. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/.storybook/preview.ts +8 -0
  304. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/.storybook/vitest.setup.ts +2 -1
  305. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/package-lock.json +186 -311
  306. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/package.json +13 -13
  307. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentPreview.svelte +273 -0
  308. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/{ChatAttachmentFilePreview.svelte → ChatAttachmentThumbnailFile.svelte} +19 -29
  309. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/{ChatAttachmentImagePreview.svelte → ChatAttachmentThumbnailImage.svelte} +5 -14
  310. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentsList.svelte +145 -63
  311. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentsViewAll.svelte +190 -0
  312. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatForm.svelte +7 -1
  313. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/{ChatFormActions.svelte → ChatFormActions/ChatFormActions.svelte} +5 -3
  314. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte +1 -7
  315. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessage.svelte +48 -1
  316. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageActions.svelte +13 -4
  317. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte +133 -3
  318. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageUser.svelte +29 -6
  319. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessages.svelte +26 -2
  320. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatScreen/ChatScreen.svelte +46 -27
  321. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatScreen/ChatScreenHeader.svelte +2 -2
  322. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/{ChatProcessingInfo.svelte → ChatScreen/ChatScreenProcessingInfo.svelte} +2 -4
  323. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/{ChatSettingsDialog.svelte → ChatSettings.svelte} +147 -157
  324. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/ChatSettingsFields.svelte +24 -8
  325. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/{ImportExportTab.svelte → ChatSettingsImportExportTab.svelte} +3 -3
  326. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSidebar/ChatSidebar.svelte +2 -2
  327. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/DialogChatAttachmentPreview.svelte +78 -0
  328. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/DialogChatAttachmentsViewAll.svelte +51 -0
  329. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/DialogChatSettings.svelte +37 -0
  330. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/DialogConversationSelection.svelte +68 -0
  331. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/index.ts +36 -26
  332. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/misc/ConversationSelection.svelte +205 -0
  333. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/misc/MarkdownContent.svelte +2 -0
  334. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/misc/RemoveButton.svelte +26 -0
  335. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/constants/settings-config.ts +11 -2
  336. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/constants/table-html-restorer.ts +20 -0
  337. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/markdown/table-html-restorer.ts +181 -0
  338. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/services/chat.ts +153 -13
  339. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/stores/chat.svelte.ts +298 -2
  340. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/stores/database.ts +2 -0
  341. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/api.d.ts +19 -0
  342. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/chat.d.ts +23 -0
  343. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/database.d.ts +1 -0
  344. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/settings.d.ts +9 -1
  345. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/routes/+layout.svelte +4 -4
  346. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/ChatForm.stories.svelte +1 -1
  347. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/ChatSettings.stories.svelte +19 -0
  348. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/ChatSidebar.stories.svelte +1 -1
  349. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/MarkdownContent.stories.svelte +25 -26
  350. vendor_llama_cpp_pydist/llama.cpp/vendor/cpp-httplib/CMakeLists.txt +147 -0
  351. vendor_llama_cpp_pydist/llama.cpp/vendor/cpp-httplib/httplib.cpp +9584 -0
  352. vendor_llama_cpp_pydist/llama.cpp/vendor/cpp-httplib/httplib.h +33 -9342
  353. vendor_llama_cpp_pydist/llama.cpp/.github/workflows/build-amd.yml +0 -52
  354. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/Doxyfile +0 -2579
  355. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/moe-expert-reduce.cu +0 -168
  356. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/moe-expert-reduce.cuh +0 -11
  357. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentPreviewDialog.svelte +0 -314
  358. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/ConversationSelectionDialog.svelte +0 -249
  359. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/ChatSettingsDialog.stories.svelte +0 -26
  360. {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/WHEEL +0 -0
  361. {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/licenses/LICENSE +0 -0
  362. {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/top_level.txt +0 -0
  363. /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/{ChatFormActionFileAttachments.svelte → ChatFormActions/ChatFormActionFileAttachments.svelte} +0 -0
  364. /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/{ChatFormActionRecord.svelte → ChatFormActions/ChatFormActionRecord.svelte} +0 -0
  365. /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/{ParameterSourceIndicator.svelte → ChatSettingsParameterSourceIndicator.svelte} +0 -0
  366. /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/{ChatErrorDialog.svelte → DialogChatError.svelte} +0 -0
  367. /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/{ConfirmationDialog.svelte → DialogConfirmation.svelte} +0 -0
  368. /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/{ConversationTitleUpdateDialog.svelte → DialogConversationTitleUpdate.svelte} +0 -0
  369. /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/{EmptyFileAlertDialog.svelte → DialogEmptyFileAlert.svelte} +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: llama_cpp_pydist
3
- Version: 0.14.0
3
+ Version: 0.16.0
4
4
  Summary: A Python package for Llama CPP.
5
5
  Home-page: https://github.com/shamitv/llama_cpp
6
6
  Author: Shamit Verma
@@ -146,6 +146,194 @@ For instructions on how to build the package from source, update the `llama.cpp`
146
146
 
147
147
  # Changelog
148
148
 
149
+ ## 2025-12-01: Update to llama.cpp b7213
150
+
151
+ - b7090 (b7090) – 2025-11-18 – https://github.com/ggml-org/llama.cpp/releases/tag/b7090
152
+ - b7091 (b7091) – 2025-11-18 – https://github.com/ggml-org/llama.cpp/releases/tag/b7091
153
+ - b7096 (b7096) – 2025-11-18 – https://github.com/ggml-org/llama.cpp/releases/tag/b7096
154
+ - b7097 (b7097) – 2025-11-18 – https://github.com/ggml-org/llama.cpp/releases/tag/b7097
155
+ - b7100 (b7100) – 2025-11-19 – https://github.com/ggml-org/llama.cpp/releases/tag/b7100
156
+ - b7101 (b7101) – 2025-11-19 – https://github.com/ggml-org/llama.cpp/releases/tag/b7101
157
+ - b7102 (b7102) – 2025-11-19 – https://github.com/ggml-org/llama.cpp/releases/tag/b7102
158
+ - b7103 (b7103) – 2025-11-19 – https://github.com/ggml-org/llama.cpp/releases/tag/b7103
159
+ - b7106 (b7106) – 2025-11-19 – https://github.com/ggml-org/llama.cpp/releases/tag/b7106
160
+ - b7107 (b7107) – 2025-11-19 – https://github.com/ggml-org/llama.cpp/releases/tag/b7107
161
+ - b7108 (b7108) – 2025-11-19 – https://github.com/ggml-org/llama.cpp/releases/tag/b7108
162
+ - b7109 (b7109) – 2025-11-20 – https://github.com/ggml-org/llama.cpp/releases/tag/b7109
163
+ - b7110 (b7110) – 2025-11-20 – https://github.com/ggml-org/llama.cpp/releases/tag/b7110
164
+ - b7111 (b7111) – 2025-11-20 – https://github.com/ggml-org/llama.cpp/releases/tag/b7111
165
+ - b7112 (b7112) – 2025-11-20 – https://github.com/ggml-org/llama.cpp/releases/tag/b7112
166
+ - b7113 (b7113) – 2025-11-20 – https://github.com/ggml-org/llama.cpp/releases/tag/b7113
167
+ - b7117 (b7117) – 2025-11-20 – https://github.com/ggml-org/llama.cpp/releases/tag/b7117
168
+ - b7118 (b7118) – 2025-11-20 – https://github.com/ggml-org/llama.cpp/releases/tag/b7118
169
+ - b7120 (b7120) – 2025-11-20 – https://github.com/ggml-org/llama.cpp/releases/tag/b7120
170
+ - b7122 (b7122) – 2025-11-21 – https://github.com/ggml-org/llama.cpp/releases/tag/b7122
171
+ - b7123 (b7123) – 2025-11-21 – https://github.com/ggml-org/llama.cpp/releases/tag/b7123
172
+ - b7124 (b7124) – 2025-11-21 – https://github.com/ggml-org/llama.cpp/releases/tag/b7124
173
+ - b7126 (b7126) – 2025-11-21 – https://github.com/ggml-org/llama.cpp/releases/tag/b7126
174
+ - b7127 (b7127) – 2025-11-21 – https://github.com/ggml-org/llama.cpp/releases/tag/b7127
175
+ - b7128 (b7128) – 2025-11-21 – https://github.com/ggml-org/llama.cpp/releases/tag/b7128
176
+ - b7129 (b7129) – 2025-11-22 – https://github.com/ggml-org/llama.cpp/releases/tag/b7129
177
+ - b7130 (b7130) – 2025-11-22 – https://github.com/ggml-org/llama.cpp/releases/tag/b7130
178
+ - b7132 (b7132) – 2025-11-23 – https://github.com/ggml-org/llama.cpp/releases/tag/b7132
179
+ - b7134 (b7134) – 2025-11-23 – https://github.com/ggml-org/llama.cpp/releases/tag/b7134
180
+ - b7136 (b7136) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7136
181
+ - b7137 (b7137) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7137
182
+ - b7138 (b7138) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7138
183
+ - b7139 (b7139) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7139
184
+ - b7140 (b7140) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7140
185
+ - b7141 (b7141) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7141
186
+ - b7142 (b7142) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7142
187
+ - b7144 (b7144) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7144
188
+ - b7146 (b7146) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7146
189
+ - b7148 (b7148) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7148
190
+ - b7149 (b7149) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7149
191
+ - b7150 (b7150) – 2025-11-24 – https://github.com/ggml-org/llama.cpp/releases/tag/b7150
192
+ - b7151 (b7151) – 2025-11-25 – https://github.com/ggml-org/llama.cpp/releases/tag/b7151
193
+ - b7152 (b7152) – 2025-11-25 – https://github.com/ggml-org/llama.cpp/releases/tag/b7152
194
+ - b7154 (b7154) – 2025-11-25 – https://github.com/ggml-org/llama.cpp/releases/tag/b7154
195
+ - b7157 (b7157) – 2025-11-25 – https://github.com/ggml-org/llama.cpp/releases/tag/b7157
196
+ - b7158 (b7158) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7158
197
+ - b7159 (b7159) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7159
198
+ - b7160 (b7160) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7160
199
+ - b7161 (b7161) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7161
200
+ - b7162 (b7162) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7162
201
+ - b7163 (b7163) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7163
202
+ - b7164 (b7164) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7164
203
+ - b7165 (b7165) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7165
204
+ - b7166 (b7166) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7166
205
+ - b7167 (b7167) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7167
206
+ - b7168 (b7168) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7168
207
+ - b7169 (b7169) – 2025-11-26 – https://github.com/ggml-org/llama.cpp/releases/tag/b7169
208
+ - b7170 (b7170) – 2025-11-27 – https://github.com/ggml-org/llama.cpp/releases/tag/b7170
209
+ - b7171 (b7171) – 2025-11-27 – https://github.com/ggml-org/llama.cpp/releases/tag/b7171
210
+ - b7172 (b7172) – 2025-11-27 – https://github.com/ggml-org/llama.cpp/releases/tag/b7172
211
+ - b7175 (b7175) – 2025-11-27 – https://github.com/ggml-org/llama.cpp/releases/tag/b7175
212
+ - b7176 (b7176) – 2025-11-27 – https://github.com/ggml-org/llama.cpp/releases/tag/b7176
213
+ - b7177 (b7177) – 2025-11-27 – https://github.com/ggml-org/llama.cpp/releases/tag/b7177
214
+ - b7178 (b7178) – 2025-11-27 – https://github.com/ggml-org/llama.cpp/releases/tag/b7178
215
+ - b7179 (b7179) – 2025-11-27 – https://github.com/ggml-org/llama.cpp/releases/tag/b7179
216
+ - b7180 (b7180) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7180
217
+ - b7181 (b7181) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7181
218
+ - b7182 (b7182) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7182
219
+ - b7183 (b7183) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7183
220
+ - b7184 (b7184) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7184
221
+ - b7185 (b7185) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7185
222
+ - b7186 (b7186) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7186
223
+ - b7187 (b7187) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7187
224
+ - b7188 (b7188) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7188
225
+ - b7189 (b7189) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7189
226
+ - b7190 (b7190) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7190
227
+ - b7191 (b7191) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7191
228
+ - b7192 (b7192) – 2025-11-28 – https://github.com/ggml-org/llama.cpp/releases/tag/b7192
229
+ - b7194 (b7194) – 2025-11-29 – https://github.com/ggml-org/llama.cpp/releases/tag/b7194
230
+ - b7195 (b7195) – 2025-11-29 – https://github.com/ggml-org/llama.cpp/releases/tag/b7195
231
+ - b7196 (b7196) – 2025-11-29 – https://github.com/ggml-org/llama.cpp/releases/tag/b7196
232
+ - b7197 (b7197) – 2025-11-29 – https://github.com/ggml-org/llama.cpp/releases/tag/b7197
233
+ - b7198 (b7198) – 2025-11-29 – https://github.com/ggml-org/llama.cpp/releases/tag/b7198
234
+ - b7199 (b7199) – 2025-11-29 – https://github.com/ggml-org/llama.cpp/releases/tag/b7199
235
+ - b7200 (b7200) – 2025-11-29 – https://github.com/ggml-org/llama.cpp/releases/tag/b7200
236
+ - b7201 (b7201) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7201
237
+ - b7202 (b7202) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7202
238
+ - b7203 (b7203) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7203
239
+ - b7204 (b7204) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7204
240
+ - b7205 (b7205) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7205
241
+ - b7206 (b7206) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7206
242
+ - b7207 (b7207) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7207
243
+ - b7208 (b7208) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7208
244
+ - b7209 (b7209) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7209
245
+ - b7210 (b7210) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7210
246
+ - b7211 (b7211) – 2025-11-30 – https://github.com/ggml-org/llama.cpp/releases/tag/b7211
247
+ - b7213 (b7213) – 2025-12-01 – https://github.com/ggml-org/llama.cpp/releases/tag/b7213
248
+
249
+
250
+ ## 2025-11-14: Update to llama.cpp b7058
251
+
252
+ - b6959 (b6959) – 2025-11-05 – https://github.com/ggml-org/llama.cpp/releases/tag/b6959
253
+ - b6960 (b6960) – 2025-11-05 – https://github.com/ggml-org/llama.cpp/releases/tag/b6960
254
+ - b6961 (b6961) – 2025-11-05 – https://github.com/ggml-org/llama.cpp/releases/tag/b6961
255
+ - b6962 (b6962) – 2025-11-05 – https://github.com/ggml-org/llama.cpp/releases/tag/b6962
256
+ - b6963 (b6963) – 2025-11-06 – https://github.com/ggml-org/llama.cpp/releases/tag/b6963
257
+ - b6965 (b6965) – 2025-11-06 – https://github.com/ggml-org/llama.cpp/releases/tag/b6965
258
+ - b6966 (b6966) – 2025-11-06 – https://github.com/ggml-org/llama.cpp/releases/tag/b6966
259
+ - b6967 (b6967) – 2025-11-06 – https://github.com/ggml-org/llama.cpp/releases/tag/b6967
260
+ - b6968 (b6968) – 2025-11-06 – https://github.com/ggml-org/llama.cpp/releases/tag/b6968
261
+ - b6969 (b6969) – 2025-11-06 – https://github.com/ggml-org/llama.cpp/releases/tag/b6969
262
+ - b6970 (b6970) – 2025-11-06 – https://github.com/ggml-org/llama.cpp/releases/tag/b6970
263
+ - b6971 (b6971) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6971
264
+ - b6972 (b6972) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6972
265
+ - b6973 (b6973) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6973
266
+ - b6974 (b6974) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6974
267
+ - b6975 (b6975) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6975
268
+ - b6976 (b6976) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6976
269
+ - b6977 (b6977) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6977
270
+ - b6978 (b6978) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6978
271
+ - b6979 (b6979) – 2025-11-07 – https://github.com/ggml-org/llama.cpp/releases/tag/b6979
272
+ - b6980 (b6980) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6980
273
+ - b6981 (b6981) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6981
274
+ - b6982 (b6982) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6982
275
+ - b6983 (b6983) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6983
276
+ - b6984 (b6984) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6984
277
+ - b6985 (b6985) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6985
278
+ - b6986 (b6986) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6986
279
+ - b6987 (b6987) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6987
280
+ - b6988 (b6988) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6988
281
+ - b6989 (b6989) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6989
282
+ - b6990 (b6990) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6990
283
+ - b6992 (b6992) – 2025-11-08 – https://github.com/ggml-org/llama.cpp/releases/tag/b6992
284
+ - b6993 (b6993) – 2025-11-09 – https://github.com/ggml-org/llama.cpp/releases/tag/b6993
285
+ - b6994 (b6994) – 2025-11-09 – https://github.com/ggml-org/llama.cpp/releases/tag/b6994
286
+ - b6995 (b6995) – 2025-11-09 – https://github.com/ggml-org/llama.cpp/releases/tag/b6995
287
+ - b6996 (b6996) – 2025-11-09 – https://github.com/ggml-org/llama.cpp/releases/tag/b6996
288
+ - b6999 (b6999) – 2025-11-09 – https://github.com/ggml-org/llama.cpp/releases/tag/b6999
289
+ - b7002 (b7002) – 2025-11-09 – https://github.com/ggml-org/llama.cpp/releases/tag/b7002
290
+ - b7003 (b7003) – 2025-11-09 – https://github.com/ggml-org/llama.cpp/releases/tag/b7003
291
+ - b7005 (b7005) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7005
292
+ - b7007 (b7007) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7007
293
+ - b7008 (b7008) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7008
294
+ - b7009 (b7009) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7009
295
+ - b7010 (b7010) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7010
296
+ - b7011 (b7011) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7011
297
+ - b7012 (b7012) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7012
298
+ - b7013 (b7013) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7013
299
+ - b7014 (b7014) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7014
300
+ - b7015 (b7015) – 2025-11-10 – https://github.com/ggml-org/llama.cpp/releases/tag/b7015
301
+ - b7016 (b7016) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7016
302
+ - b7017 (b7017) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7017
303
+ - b7018 (b7018) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7018
304
+ - b7020 (b7020) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7020
305
+ - b7021 (b7021) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7021
306
+ - b7022 (b7022) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7022
307
+ - b7023 (b7023) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7023
308
+ - b7024 (b7024) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7024
309
+ - b7025 (b7025) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7025
310
+ - b7027 (b7027) – 2025-11-11 – https://github.com/ggml-org/llama.cpp/releases/tag/b7027
311
+ - b7028 (b7028) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7028
312
+ - b7030 (b7030) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7030
313
+ - b7031 (b7031) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7031
314
+ - b7032 (b7032) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7032
315
+ - b7033 (b7033) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7033
316
+ - b7034 (b7034) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7034
317
+ - b7035 (b7035) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7035
318
+ - b7037 (b7037) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7037
319
+ - b7039 (b7039) – 2025-11-12 – https://github.com/ggml-org/llama.cpp/releases/tag/b7039
320
+ - b7041 (b7041) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7041
321
+ - b7042 (b7042) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7042
322
+ - b7044 (b7044) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7044
323
+ - b7045 (b7045) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7045
324
+ - b7046 (b7046) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7046
325
+ - b7047 (b7047) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7047
326
+ - b7048 (b7048) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7048
327
+ - b7049 (b7049) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7049
328
+ - b7050 (b7050) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7050
329
+ - b7051 (b7051) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7051
330
+ - b7052 (b7052) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7052
331
+ - b7053 (b7053) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7053
332
+ - b7054 (b7054) – 2025-11-13 – https://github.com/ggml-org/llama.cpp/releases/tag/b7054
333
+ - b7057 (b7057) – 2025-11-14 – https://github.com/ggml-org/llama.cpp/releases/tag/b7057
334
+ - b7058 (b7058) – 2025-11-14 – https://github.com/ggml-org/llama.cpp/releases/tag/b7058
335
+
336
+
149
337
  ## 2025-11-05: Update to llama.cpp b6957
150
338
 
151
339
  - b6919 (b6919) – 2025-11-01 – https://github.com/ggml-org/llama.cpp/releases/tag/b6919