llama-cpp-pydist 0.13.0__py3-none-any.whl → 0.14.0__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 (136) hide show
  1. llama_cpp/binaries/{llama-b6916-bin-win-cpu-x64.zip → llama-b6957-bin-win-cpu-x64.zip} +0 -0
  2. {llama_cpp_pydist-0.13.0.dist-info → llama_cpp_pydist-0.14.0.dist-info}/METADATA +31 -1
  3. {llama_cpp_pydist-0.13.0.dist-info → llama_cpp_pydist-0.14.0.dist-info}/RECORD +136 -128
  4. vendor_llama_cpp_pydist/llama.cpp/.devops/s390x.Dockerfile +4 -1
  5. vendor_llama_cpp_pydist/llama.cpp/.github/labeler.yml +4 -0
  6. vendor_llama_cpp_pydist/llama.cpp/.github/workflows/build-linux-cross.yml +37 -37
  7. vendor_llama_cpp_pydist/llama.cpp/.github/workflows/release.yml +2 -2
  8. vendor_llama_cpp_pydist/llama.cpp/README.md +3 -4
  9. vendor_llama_cpp_pydist/llama.cpp/common/arg.cpp +14 -0
  10. vendor_llama_cpp_pydist/llama.cpp/common/chat.cpp +17 -2
  11. vendor_llama_cpp_pydist/llama.cpp/common/common.h +6 -0
  12. vendor_llama_cpp_pydist/llama.cpp/convert_hf_to_gguf.py +143 -0
  13. vendor_llama_cpp_pydist/llama.cpp/docs/backend/OPENCL.md +25 -3
  14. vendor_llama_cpp_pydist/llama.cpp/docs/docker.md +3 -3
  15. vendor_llama_cpp_pydist/llama.cpp/docs/ops/CUDA.csv +1620 -0
  16. vendor_llama_cpp_pydist/llama.cpp/docs/ops.md +5 -5
  17. vendor_llama_cpp_pydist/llama.cpp/ggml/include/ggml.h +1 -0
  18. vendor_llama_cpp_pydist/llama.cpp/ggml/src/CMakeLists.txt +6 -3
  19. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/CMakeLists.txt +10 -3
  20. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/loongarch/quants.c +4 -5
  21. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/s390/cpu-feats.cpp +50 -0
  22. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/ggml-cpu-impl.h +3 -1
  23. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/ops.cpp +57 -8
  24. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/repack.cpp +25 -0
  25. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h +25 -25
  26. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn-tile.cu +4 -0
  27. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn-tile.cuh +29 -2
  28. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn.cu +3 -2
  29. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu +33 -0
  30. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq72-dv72.cu +5 -0
  31. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/template-instances/generate_cu_files.py +3 -1
  32. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/unary.cu +32 -0
  33. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/unary.cuh +8 -0
  34. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/ops-utils.h +17 -17
  35. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-device.m +1 -0
  36. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal.metal +8 -0
  37. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/ggml-opencl.cpp +6 -0
  38. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/rope.cl +50 -24
  39. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/repeat_back.cpp +45 -25
  40. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/ggml-vulkan.cpp +274 -406
  41. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/ggml-webgpu.cpp +65 -23
  42. vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/{set_rows.wgsl → set_rows.tmpl.wgsl} +38 -7
  43. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/constants.py +21 -0
  44. vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/tensor_mapping.py +2 -0
  45. vendor_llama_cpp_pydist/llama.cpp/include/llama.h +4 -3
  46. vendor_llama_cpp_pydist/llama.cpp/scripts/bench-models.sh +74 -0
  47. vendor_llama_cpp_pydist/llama.cpp/scripts/sync-ggml.last +1 -1
  48. vendor_llama_cpp_pydist/llama.cpp/src/CMakeLists.txt +1 -0
  49. vendor_llama_cpp_pydist/llama.cpp/src/llama-arch.cpp +18 -0
  50. vendor_llama_cpp_pydist/llama.cpp/src/llama-arch.h +1 -0
  51. vendor_llama_cpp_pydist/llama.cpp/src/llama-chat.cpp +32 -0
  52. vendor_llama_cpp_pydist/llama.cpp/src/llama-chat.h +1 -0
  53. vendor_llama_cpp_pydist/llama.cpp/src/llama-context.cpp +27 -10
  54. vendor_llama_cpp_pydist/llama.cpp/src/llama-context.h +5 -5
  55. vendor_llama_cpp_pydist/llama.cpp/src/llama-cparams.h +1 -0
  56. vendor_llama_cpp_pydist/llama.cpp/src/llama-model.cpp +62 -10
  57. vendor_llama_cpp_pydist/llama.cpp/src/models/gemma2-iswa.cpp +113 -113
  58. vendor_llama_cpp_pydist/llama.cpp/src/models/gemma3-iswa.cpp +116 -116
  59. vendor_llama_cpp_pydist/llama.cpp/src/models/glm4-moe.cpp +139 -139
  60. vendor_llama_cpp_pydist/llama.cpp/src/models/grok.cpp +133 -134
  61. vendor_llama_cpp_pydist/llama.cpp/src/models/hunyuan-dense.cpp +113 -113
  62. vendor_llama_cpp_pydist/llama.cpp/src/models/hunyuan-moe.cpp +135 -135
  63. vendor_llama_cpp_pydist/llama.cpp/src/models/internlm2.cpp +97 -98
  64. vendor_llama_cpp_pydist/llama.cpp/src/models/jais.cpp +70 -70
  65. vendor_llama_cpp_pydist/llama.cpp/src/models/jamba.cpp +97 -98
  66. vendor_llama_cpp_pydist/llama.cpp/src/models/llada-moe.cpp +113 -114
  67. vendor_llama_cpp_pydist/llama.cpp/src/models/llada.cpp +71 -73
  68. vendor_llama_cpp_pydist/llama.cpp/src/models/llama.cpp +128 -129
  69. vendor_llama_cpp_pydist/llama.cpp/src/models/minicpm3.cpp +177 -178
  70. vendor_llama_cpp_pydist/llama.cpp/src/models/models.h +4 -0
  71. vendor_llama_cpp_pydist/llama.cpp/src/models/nemotron.cpp +99 -99
  72. vendor_llama_cpp_pydist/llama.cpp/src/models/neo-bert.cpp +97 -97
  73. vendor_llama_cpp_pydist/llama.cpp/src/models/olmo.cpp +98 -98
  74. vendor_llama_cpp_pydist/llama.cpp/src/models/olmo2.cpp +122 -123
  75. vendor_llama_cpp_pydist/llama.cpp/src/models/olmoe.cpp +107 -107
  76. vendor_llama_cpp_pydist/llama.cpp/src/models/openai-moe-iswa.cpp +106 -106
  77. vendor_llama_cpp_pydist/llama.cpp/src/models/openelm.cpp +105 -105
  78. vendor_llama_cpp_pydist/llama.cpp/src/models/orion.cpp +113 -113
  79. vendor_llama_cpp_pydist/llama.cpp/src/models/pangu-embedded.cpp +121 -0
  80. vendor_llama_cpp_pydist/llama.cpp/src/models/phi3.cpp +128 -129
  81. vendor_llama_cpp_pydist/llama.cpp/src/models/plamo.cpp +100 -100
  82. vendor_llama_cpp_pydist/llama.cpp/src/models/plm.cpp +154 -154
  83. vendor_llama_cpp_pydist/llama.cpp/src/models/qwen2.cpp +108 -109
  84. vendor_llama_cpp_pydist/llama.cpp/src/models/qwen2moe.cpp +127 -127
  85. vendor_llama_cpp_pydist/llama.cpp/src/models/qwen2vl.cpp +107 -107
  86. vendor_llama_cpp_pydist/llama.cpp/src/models/qwen3.cpp +107 -107
  87. vendor_llama_cpp_pydist/llama.cpp/src/models/qwen3moe.cpp +115 -115
  88. vendor_llama_cpp_pydist/llama.cpp/src/models/refact.cpp +76 -76
  89. vendor_llama_cpp_pydist/llama.cpp/src/models/seed-oss.cpp +100 -100
  90. vendor_llama_cpp_pydist/llama.cpp/src/models/smallthinker.cpp +92 -92
  91. vendor_llama_cpp_pydist/llama.cpp/src/models/smollm3.cpp +100 -100
  92. vendor_llama_cpp_pydist/llama.cpp/src/models/starcoder.cpp +81 -81
  93. vendor_llama_cpp_pydist/llama.cpp/src/models/starcoder2.cpp +93 -93
  94. vendor_llama_cpp_pydist/llama.cpp/src/models/t5-dec.cpp +135 -135
  95. vendor_llama_cpp_pydist/llama.cpp/src/models/t5-enc.cpp +77 -77
  96. vendor_llama_cpp_pydist/llama.cpp/src/models/wavtokenizer-dec.cpp +106 -106
  97. vendor_llama_cpp_pydist/llama.cpp/src/models/xverse.cpp +89 -89
  98. vendor_llama_cpp_pydist/llama.cpp/tests/test-backend-ops.cpp +21 -2
  99. vendor_llama_cpp_pydist/llama.cpp/tests/test-thread-safety.cpp +8 -1
  100. vendor_llama_cpp_pydist/llama.cpp/tools/batched-bench/batched-bench.cpp +0 -2
  101. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip-impl.h +2 -0
  102. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip.cpp +239 -47
  103. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip.h +10 -0
  104. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd-cli.cpp +7 -4
  105. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd.cpp +29 -14
  106. vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd.h +5 -0
  107. vendor_llama_cpp_pydist/llama.cpp/tools/server/README.md +1 -1
  108. vendor_llama_cpp_pydist/llama.cpp/tools/server/public/index.html.gz +0 -0
  109. vendor_llama_cpp_pydist/llama.cpp/tools/server/server.cpp +89 -21
  110. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_chat_completion.py +4 -4
  111. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_completion.py +31 -0
  112. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_infill.py +2 -2
  113. vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/utils.py +3 -0
  114. vendor_llama_cpp_pydist/llama.cpp/tools/server/utils.hpp +2 -1
  115. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/package-lock.json +361 -0
  116. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/package.json +1 -0
  117. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentPreviewDialog.svelte +9 -0
  118. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte +2 -2
  119. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/misc/MarkdownContent.svelte +3 -12
  120. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/constants/latex-protection.ts +35 -0
  121. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/services/chat.ts +16 -4
  122. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/stores/chat.svelte.ts +52 -2
  123. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/stores/server.svelte.ts +113 -64
  124. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/api.d.ts +1 -0
  125. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/settings.d.ts +1 -0
  126. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/utils/latex-protection.test.ts +355 -0
  127. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/utils/latex-protection.ts +267 -0
  128. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/fixtures/math-formulas.ts +65 -0
  129. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/styles/katex-custom.scss +13 -0
  130. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/svelte.config.js +3 -0
  131. vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/vite.config.ts +28 -3
  132. vendor_llama_cpp_pydist/llama.cpp/vendor/minja/chat-template.hpp +9 -2
  133. vendor_llama_cpp_pydist/llama.cpp/vendor/minja/minja.hpp +5 -7
  134. {llama_cpp_pydist-0.13.0.dist-info → llama_cpp_pydist-0.14.0.dist-info}/WHEEL +0 -0
  135. {llama_cpp_pydist-0.13.0.dist-info → llama_cpp_pydist-0.14.0.dist-info}/licenses/LICENSE +0 -0
  136. {llama_cpp_pydist-0.13.0.dist-info → llama_cpp_pydist-0.14.0.dist-info}/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: llama_cpp_pydist
3
- Version: 0.13.0
3
+ Version: 0.14.0
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 +146,36 @@ For instructions on how to build the package from source, update the `llama.cpp`
146
146
 
147
147
  # Changelog
148
148
 
149
+ ## 2025-11-05: Update to llama.cpp b6957
150
+
151
+ - b6919 (b6919) – 2025-11-01 – https://github.com/ggml-org/llama.cpp/releases/tag/b6919
152
+ - b6920 (b6920) – 2025-11-02 – https://github.com/ggml-org/llama.cpp/releases/tag/b6920
153
+ - b6922 (b6922) – 2025-11-02 – https://github.com/ggml-org/llama.cpp/releases/tag/b6922
154
+ - b6923 (b6923) – 2025-11-02 – https://github.com/ggml-org/llama.cpp/releases/tag/b6923
155
+ - b6924 (b6924) – 2025-11-02 – https://github.com/ggml-org/llama.cpp/releases/tag/b6924
156
+ - b6927 (b6927) – 2025-11-02 – https://github.com/ggml-org/llama.cpp/releases/tag/b6927
157
+ - b6929 (b6929) – 2025-11-02 – https://github.com/ggml-org/llama.cpp/releases/tag/b6929
158
+ - b6931 (b6931) – 2025-11-03 – https://github.com/ggml-org/llama.cpp/releases/tag/b6931
159
+ - b6932 (b6932) – 2025-11-03 – https://github.com/ggml-org/llama.cpp/releases/tag/b6932
160
+ - b6933 (b6933) – 2025-11-03 – https://github.com/ggml-org/llama.cpp/releases/tag/b6933
161
+ - b6934 (b6934) – 2025-11-03 – https://github.com/ggml-org/llama.cpp/releases/tag/b6934
162
+ - b6935 (b6935) – 2025-11-03 – https://github.com/ggml-org/llama.cpp/releases/tag/b6935
163
+ - b6936 (b6936) – 2025-11-03 – https://github.com/ggml-org/llama.cpp/releases/tag/b6936
164
+ - b6937 (b6937) – 2025-11-03 – https://github.com/ggml-org/llama.cpp/releases/tag/b6937
165
+ - b6940 (b6940) – 2025-11-03 – https://github.com/ggml-org/llama.cpp/releases/tag/b6940
166
+ - b6941 (b6941) – 2025-11-04 – https://github.com/ggml-org/llama.cpp/releases/tag/b6941
167
+ - b6942 (b6942) – 2025-11-04 – https://github.com/ggml-org/llama.cpp/releases/tag/b6942
168
+ - b6943 (b6943) – 2025-11-04 – https://github.com/ggml-org/llama.cpp/releases/tag/b6943
169
+ - b6945 (b6945) – 2025-11-04 – https://github.com/ggml-org/llama.cpp/releases/tag/b6945
170
+ - b6947 (b6947) – 2025-11-04 – https://github.com/ggml-org/llama.cpp/releases/tag/b6947
171
+ - b6948 (b6948) – 2025-11-04 – https://github.com/ggml-org/llama.cpp/releases/tag/b6948
172
+ - b6949 (b6949) – 2025-11-04 – https://github.com/ggml-org/llama.cpp/releases/tag/b6949
173
+ - b6953 (b6953) – 2025-11-05 – https://github.com/ggml-org/llama.cpp/releases/tag/b6953
174
+ - b6954 (b6954) – 2025-11-05 – https://github.com/ggml-org/llama.cpp/releases/tag/b6954
175
+ - b6955 (b6955) – 2025-11-05 – https://github.com/ggml-org/llama.cpp/releases/tag/b6955
176
+ - b6957 (b6957) – 2025-11-05 – https://github.com/ggml-org/llama.cpp/releases/tag/b6957
177
+
178
+
149
179
  ## 2025-11-01: Update to llama.cpp b6916
150
180
 
151
181
  - b6904 (b6904) – 2025-10-31 – https://github.com/ggml-org/llama.cpp/releases/tag/b6904