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.
- llama_cpp/binaries/{llama-b6957-bin-win-cpu-x64.zip → llama-b7213-bin-win-cpu-x64.zip} +0 -0
- {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/METADATA +189 -1
- {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/RECORD +362 -296
- vendor_llama_cpp_pydist/llama.cpp/.devops/cann.Dockerfile +6 -7
- vendor_llama_cpp_pydist/llama.cpp/.devops/cpu.Dockerfile +1 -1
- vendor_llama_cpp_pydist/llama.cpp/.devops/cuda.Dockerfile +1 -1
- vendor_llama_cpp_pydist/llama.cpp/.devops/intel.Dockerfile +1 -1
- vendor_llama_cpp_pydist/llama.cpp/.devops/musa.Dockerfile +1 -1
- vendor_llama_cpp_pydist/llama.cpp/.devops/nix/package.nix +2 -0
- vendor_llama_cpp_pydist/llama.cpp/.devops/rocm.Dockerfile +1 -1
- vendor_llama_cpp_pydist/llama.cpp/.devops/vulkan.Dockerfile +6 -23
- vendor_llama_cpp_pydist/llama.cpp/.editorconfig +8 -0
- vendor_llama_cpp_pydist/llama.cpp/.github/copilot-instructions.md +1 -1
- vendor_llama_cpp_pydist/llama.cpp/.github/workflows/build.yml +142 -102
- vendor_llama_cpp_pydist/llama.cpp/.github/workflows/check-vendor.yml +52 -0
- vendor_llama_cpp_pydist/llama.cpp/.github/workflows/release.yml +46 -0
- vendor_llama_cpp_pydist/llama.cpp/.github/workflows/server.yml +10 -17
- vendor_llama_cpp_pydist/llama.cpp/.gitignore +45 -63
- vendor_llama_cpp_pydist/llama.cpp/CMakeLists.txt +4 -0
- vendor_llama_cpp_pydist/llama.cpp/CODEOWNERS +8 -23
- vendor_llama_cpp_pydist/llama.cpp/CONTRIBUTING.md +1 -0
- vendor_llama_cpp_pydist/llama.cpp/README.md +2 -0
- vendor_llama_cpp_pydist/llama.cpp/SECURITY.md +2 -0
- vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547.html +35144 -0
- vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547.json +6 -0
- vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547_allresults.json +2896 -0
- vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/dgx-spark.md +264 -0
- vendor_llama_cpp_pydist/llama.cpp/benches/dgx-spark/run-aime-120b-t8-x8-high.log +11 -0
- vendor_llama_cpp_pydist/llama.cpp/build-xcframework.sh +4 -0
- vendor_llama_cpp_pydist/llama.cpp/ci/run.sh +14 -9
- vendor_llama_cpp_pydist/llama.cpp/common/CMakeLists.txt +10 -37
- vendor_llama_cpp_pydist/llama.cpp/common/arg.cpp +63 -1001
- vendor_llama_cpp_pydist/llama.cpp/common/arg.h +2 -2
- vendor_llama_cpp_pydist/llama.cpp/common/chat-parser-xml-toolcall.cpp +861 -0
- vendor_llama_cpp_pydist/llama.cpp/common/chat-parser-xml-toolcall.h +45 -0
- vendor_llama_cpp_pydist/llama.cpp/common/chat-parser.cpp +968 -0
- vendor_llama_cpp_pydist/llama.cpp/common/chat-parser.h +10 -0
- vendor_llama_cpp_pydist/llama.cpp/common/chat.cpp +311 -889
- vendor_llama_cpp_pydist/llama.cpp/common/chat.h +6 -0
- vendor_llama_cpp_pydist/llama.cpp/common/common.cpp +97 -6
- vendor_llama_cpp_pydist/llama.cpp/common/common.h +40 -7
- vendor_llama_cpp_pydist/llama.cpp/common/download.cpp +1079 -0
- vendor_llama_cpp_pydist/llama.cpp/common/download.h +55 -0
- vendor_llama_cpp_pydist/llama.cpp/common/json-partial.cpp +19 -2
- vendor_llama_cpp_pydist/llama.cpp/common/json-schema-to-grammar.cpp +4 -2
- vendor_llama_cpp_pydist/llama.cpp/common/json-schema-to-grammar.h +2 -0
- vendor_llama_cpp_pydist/llama.cpp/common/log.cpp +20 -0
- vendor_llama_cpp_pydist/llama.cpp/common/log.h +21 -12
- vendor_llama_cpp_pydist/llama.cpp/common/sampling.cpp +60 -6
- vendor_llama_cpp_pydist/llama.cpp/convert_hf_to_gguf.py +366 -130
- vendor_llama_cpp_pydist/llama.cpp/convert_hf_to_gguf_update.py +1 -0
- vendor_llama_cpp_pydist/llama.cpp/convert_lora_to_gguf.py +11 -5
- vendor_llama_cpp_pydist/llama.cpp/docs/backend/CANN.md +6 -1
- vendor_llama_cpp_pydist/llama.cpp/docs/backend/SYCL.md +13 -0
- vendor_llama_cpp_pydist/llama.cpp/docs/build.md +42 -0
- vendor_llama_cpp_pydist/llama.cpp/docs/ops/CPU.csv +16067 -5133
- vendor_llama_cpp_pydist/llama.cpp/docs/ops/CUDA.csv +16224 -6894
- vendor_llama_cpp_pydist/llama.cpp/docs/ops/SYCL.csv +4744 -2430
- vendor_llama_cpp_pydist/llama.cpp/docs/ops/Vulkan.csv +14542 -4366
- vendor_llama_cpp_pydist/llama.cpp/docs/ops.md +58 -53
- vendor_llama_cpp_pydist/llama.cpp/ggml/CMakeLists.txt +7 -5
- vendor_llama_cpp_pydist/llama.cpp/ggml/include/ggml-rpc.h +1 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/include/ggml.h +85 -5
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/CMakeLists.txt +38 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-alloc.c +8 -3
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-backend.cpp +38 -5
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/acl_tensor.cpp +19 -10
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/acl_tensor.h +99 -19
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/aclnn_ops.cpp +1015 -755
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/aclnn_ops.h +121 -194
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/common.h +89 -158
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/ggml-cann.cpp +53 -33
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/CMakeLists.txt +91 -61
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c +428 -26
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/arm/repack.cpp +721 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/riscv/cpu-feats.cpp +38 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/riscv/quants.c +108 -49
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp +6 -6
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/arch-fallback.h +22 -2
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c +59 -16
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/kleidiai/kernels.cpp +296 -3
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/kleidiai/kernels.h +1 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp +235 -34
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/ops.cpp +414 -317
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/ops.h +5 -4
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/repack.cpp +336 -44
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/repack.h +6 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h +16 -14
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/unary-ops.cpp +16 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/unary-ops.h +2 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/vec.cpp +17 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cpu/vec.h +143 -133
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/CMakeLists.txt +1 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/argsort.cu +1 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/common.cuh +194 -18
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/convert.cuh +9 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/cpy-utils.cuh +1 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/cpy.cu +174 -45
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn-common.cuh +2 -2
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn-tile.cuh +1 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/fattn-vec.cuh +18 -18
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu +502 -44
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mma.cuh +190 -3
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmf.cu +17 -5
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmf.cuh +54 -21
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmq.cu +7 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmq.cuh +302 -139
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmvf.cu +14 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/mmvf.cuh +1 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/rope.cu +162 -60
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/rope.cuh +2 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/solve_tri.cu +203 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/solve_tri.cuh +3 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/unary.cu +16 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/unary.cuh +4 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/upscale.cu +163 -7
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/vendors/hip.h +1 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/CMakeLists.txt +10 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/ggml-hexagon.cpp +133 -395
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/act-ops.c +12 -18
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/binary-ops.c +46 -30
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/htp-dma.h +7 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/htp-msg.h +4 -4
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/htp-ops.h +11 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/hvx-exp.c +20 -6
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/hvx-inverse.c +15 -3
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/hvx-utils.c +20 -7
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/hvx-utils.h +56 -11
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/main.c +12 -3
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/ops-utils.h +33 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp/rope-ops.c +80 -7
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp-utils.c +6 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-hexagon/htp-utils.h +1 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-impl.h +1 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-context.m +5 -6
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-device.cpp +148 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-device.h +10 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-device.m +217 -10
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-impl.h +99 -2
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-ops.cpp +472 -85
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal-ops.h +3 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal.cpp +9 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-metal/ggml-metal.metal +822 -152
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/CMakeLists.txt +5 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/ggml-opencl.cpp +558 -5
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/mean.cl +39 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/mul_mm_f16_f32_kq_kqv.cl +273 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/rms_norm.cl +25 -10
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/set_rows.cl +35 -16
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/sqr.cl +53 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/sqrt.cl +53 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-opencl/kernels/ssm_conv.cl +77 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-rpc/ggml-rpc.cpp +91 -20
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/CMakeLists.txt +6 -2
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/common.hpp +26 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/concat.cpp +55 -44
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/cpy.cpp +0 -3
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/element_wise.cpp +112 -250
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/ggml-sycl.cpp +9 -11
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/pad_reflect_1d.cpp +87 -59
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-sycl/pad_reflect_1d.hpp +2 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/ggml-vulkan.cpp +2326 -1849
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/abs.comp +21 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/add1.comp +28 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/arange.comp +20 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/argsort.comp +20 -21
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/argsort_large.comp +114 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/ceil.comp +22 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/conv2d_mm.comp +39 -36
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/copy_transpose.comp +67 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/cumsum.comp +69 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl +0 -7
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/fill.comp +19 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/flash_attn.comp +33 -15
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp +34 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp +37 -19
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/floor.comp +22 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/generic_binary_head.glsl +15 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/generic_unary_head.glsl +7 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/log.comp +18 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec.comp +1 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_base.glsl +53 -38
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iface.glsl +35 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_nc.comp +8 -12
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_p021.comp +8 -12
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vecq.comp +27 -35
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vecq_funcs.glsl +379 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mm.comp +31 -2
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp +4 -4
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_funcs.glsl +62 -185
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/neg.comp +20 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/quantize_q8_1.comp +1 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rms_norm.comp +43 -1
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_funcs.glsl +227 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_head.glsl +9 -47
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_multi.comp +4 -63
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_neox.comp +4 -41
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_norm.comp +4 -41
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_params.glsl +27 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/rope_vision.comp +4 -40
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/round.comp +29 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/softplus.comp +23 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/solve_tri.comp +72 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/step.comp +22 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/sum_rows.comp +1 -24
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/sum_rows.glsl +25 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/topk_argsort.comp +113 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/topk_nary_search.comp +199 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/tri.comp +43 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/trunc.comp +22 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/upscale.comp +37 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp +110 -34
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/ggml-webgpu.cpp +313 -13
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py +6 -3
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat.tmpl.wgsl +5 -5
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl +97 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.tmpl.wgsl +247 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_subgroup_matrix.tmpl.wgsl +302 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.tmpl.wgsl +267 -0
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml.c +199 -29
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/constants.py +120 -0
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/gguf_writer.py +56 -6
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/lazy.py +8 -3
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/metadata.py +85 -0
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/scripts/gguf_convert_endian.py +12 -18
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/scripts/gguf_editor_gui.py +1 -1
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/scripts/gguf_new_metadata.py +1 -1
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/tensor_mapping.py +24 -7
- vendor_llama_cpp_pydist/llama.cpp/gguf-py/gguf/utility.py +80 -0
- vendor_llama_cpp_pydist/llama.cpp/include/llama.h +20 -0
- vendor_llama_cpp_pydist/llama.cpp/scripts/sync-ggml.last +1 -1
- vendor_llama_cpp_pydist/llama.cpp/scripts/sync_vendor.py +21 -2
- vendor_llama_cpp_pydist/llama.cpp/src/CMakeLists.txt +9 -0
- vendor_llama_cpp_pydist/llama.cpp/src/llama-arch.cpp +155 -16
- vendor_llama_cpp_pydist/llama.cpp/src/llama-arch.h +19 -0
- vendor_llama_cpp_pydist/llama.cpp/src/llama-context.cpp +16 -6
- vendor_llama_cpp_pydist/llama.cpp/src/llama-grammar.cpp +17 -9
- vendor_llama_cpp_pydist/llama.cpp/src/llama-graph.cpp +10 -12
- vendor_llama_cpp_pydist/llama.cpp/src/llama-hparams.cpp +10 -0
- vendor_llama_cpp_pydist/llama.cpp/src/llama-hparams.h +6 -3
- vendor_llama_cpp_pydist/llama.cpp/src/llama-impl.cpp +3 -3
- vendor_llama_cpp_pydist/llama.cpp/src/llama-kv-cache-iswa.cpp +3 -1
- vendor_llama_cpp_pydist/llama.cpp/src/llama-memory-recurrent.cpp +4 -3
- vendor_llama_cpp_pydist/llama.cpp/src/llama-model.cpp +300 -28
- vendor_llama_cpp_pydist/llama.cpp/src/llama-model.h +6 -0
- vendor_llama_cpp_pydist/llama.cpp/src/llama-quant.cpp +13 -5
- vendor_llama_cpp_pydist/llama.cpp/src/llama-sampling.cpp +13 -11
- vendor_llama_cpp_pydist/llama.cpp/src/llama-vocab.cpp +17 -1
- vendor_llama_cpp_pydist/llama.cpp/src/llama-vocab.h +1 -0
- vendor_llama_cpp_pydist/llama.cpp/src/models/afmoe.cpp +187 -0
- vendor_llama_cpp_pydist/llama.cpp/src/models/deepseek2.cpp +2 -1
- vendor_llama_cpp_pydist/llama.cpp/src/models/ernie4-5.cpp +4 -5
- vendor_llama_cpp_pydist/llama.cpp/src/models/lfm2.cpp +5 -3
- vendor_llama_cpp_pydist/llama.cpp/src/models/mistral3.cpp +160 -0
- vendor_llama_cpp_pydist/llama.cpp/src/models/models.h +63 -1
- vendor_llama_cpp_pydist/llama.cpp/src/models/openai-moe-iswa.cpp +2 -1
- vendor_llama_cpp_pydist/llama.cpp/src/models/qwen3next.cpp +1042 -0
- vendor_llama_cpp_pydist/llama.cpp/src/models/qwen3vl-moe.cpp +1 -2
- vendor_llama_cpp_pydist/llama.cpp/src/models/qwen3vl.cpp +1 -4
- vendor_llama_cpp_pydist/llama.cpp/src/models/rnd1.cpp +126 -0
- vendor_llama_cpp_pydist/llama.cpp/src/unicode.cpp +77 -0
- vendor_llama_cpp_pydist/llama.cpp/tests/CMakeLists.txt +1 -1
- vendor_llama_cpp_pydist/llama.cpp/tests/test-backend-ops.cpp +742 -178
- vendor_llama_cpp_pydist/llama.cpp/tests/test-chat.cpp +1033 -19
- vendor_llama_cpp_pydist/llama.cpp/tests/test-json-schema-to-grammar.cpp +26 -0
- vendor_llama_cpp_pydist/llama.cpp/tests/test-rope.cpp +6 -5
- vendor_llama_cpp_pydist/llama.cpp/tools/batched-bench/batched-bench.cpp +31 -11
- vendor_llama_cpp_pydist/llama.cpp/tools/llama-bench/llama-bench.cpp +40 -7
- vendor_llama_cpp_pydist/llama.cpp/tools/main/main.cpp +17 -3
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/CMakeLists.txt +5 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip-impl.h +5 -12
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip.cpp +100 -143
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/clip.h +0 -1
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd-cli.cpp +2 -2
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd-helper.cpp +61 -4
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd-helper.h +5 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd.cpp +10 -3
- vendor_llama_cpp_pydist/llama.cpp/tools/mtmd/mtmd.h +4 -1
- vendor_llama_cpp_pydist/llama.cpp/tools/rpc/CMakeLists.txt +4 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/CMakeLists.txt +15 -2
- vendor_llama_cpp_pydist/llama.cpp/tools/server/README.md +101 -20
- vendor_llama_cpp_pydist/llama.cpp/tools/server/public/index.html.gz +0 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/public_legacy/json-schema-to-grammar.mjs +2 -2
- vendor_llama_cpp_pydist/llama.cpp/tools/server/{utils.hpp → server-common.cpp} +998 -907
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-common.h +355 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-context.cpp +3619 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-context.h +83 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-http.cpp +394 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-http.h +78 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-queue.cpp +351 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-queue.h +146 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-task.cpp +1474 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server-task.h +460 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/server.cpp +123 -5685
- vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/conftest.py +6 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_basic.py +0 -6
- vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_compat_anthropic.py +807 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_completion.py +42 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_security.py +13 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/unit/test_speculative.py +6 -6
- vendor_llama_cpp_pydist/llama.cpp/tools/server/tests/utils.py +2 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/.gitignore +1 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/.storybook/preview.ts +8 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/.storybook/vitest.setup.ts +2 -1
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/package-lock.json +186 -311
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/package.json +13 -13
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentPreview.svelte +273 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/{ChatAttachmentFilePreview.svelte → ChatAttachmentThumbnailFile.svelte} +19 -29
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/{ChatAttachmentImagePreview.svelte → ChatAttachmentThumbnailImage.svelte} +5 -14
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentsList.svelte +145 -63
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentsViewAll.svelte +190 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatForm.svelte +7 -1
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/{ChatFormActions.svelte → ChatFormActions/ChatFormActions.svelte} +5 -3
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte +1 -7
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessage.svelte +48 -1
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageActions.svelte +13 -4
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte +133 -3
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageUser.svelte +29 -6
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessages.svelte +26 -2
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatScreen/ChatScreen.svelte +46 -27
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatScreen/ChatScreenHeader.svelte +2 -2
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/{ChatProcessingInfo.svelte → ChatScreen/ChatScreenProcessingInfo.svelte} +2 -4
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/{ChatSettingsDialog.svelte → ChatSettings.svelte} +147 -157
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/ChatSettingsFields.svelte +24 -8
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/{ImportExportTab.svelte → ChatSettingsImportExportTab.svelte} +3 -3
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSidebar/ChatSidebar.svelte +2 -2
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/DialogChatAttachmentPreview.svelte +78 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/DialogChatAttachmentsViewAll.svelte +51 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/DialogChatSettings.svelte +37 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/DialogConversationSelection.svelte +68 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/index.ts +36 -26
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/misc/ConversationSelection.svelte +205 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/misc/MarkdownContent.svelte +2 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/misc/RemoveButton.svelte +26 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/constants/settings-config.ts +11 -2
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/constants/table-html-restorer.ts +20 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/markdown/table-html-restorer.ts +181 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/services/chat.ts +153 -13
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/stores/chat.svelte.ts +298 -2
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/stores/database.ts +2 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/api.d.ts +19 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/chat.d.ts +23 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/database.d.ts +1 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/types/settings.d.ts +9 -1
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/routes/+layout.svelte +4 -4
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/ChatForm.stories.svelte +1 -1
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/ChatSettings.stories.svelte +19 -0
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/ChatSidebar.stories.svelte +1 -1
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/MarkdownContent.stories.svelte +25 -26
- vendor_llama_cpp_pydist/llama.cpp/vendor/cpp-httplib/CMakeLists.txt +147 -0
- vendor_llama_cpp_pydist/llama.cpp/vendor/cpp-httplib/httplib.cpp +9584 -0
- vendor_llama_cpp_pydist/llama.cpp/vendor/cpp-httplib/httplib.h +33 -9342
- vendor_llama_cpp_pydist/llama.cpp/.github/workflows/build-amd.yml +0 -52
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cann/Doxyfile +0 -2579
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/moe-expert-reduce.cu +0 -168
- vendor_llama_cpp_pydist/llama.cpp/ggml/src/ggml-cuda/moe-expert-reduce.cuh +0 -11
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentPreviewDialog.svelte +0 -314
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/ConversationSelectionDialog.svelte +0 -249
- vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/stories/ChatSettingsDialog.stories.svelte +0 -26
- {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/WHEEL +0 -0
- {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/licenses/LICENSE +0 -0
- {llama_cpp_pydist-0.14.0.dist-info → llama_cpp_pydist-0.16.0.dist-info}/top_level.txt +0 -0
- /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/{ChatFormActionFileAttachments.svelte → ChatFormActions/ChatFormActionFileAttachments.svelte} +0 -0
- /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatForm/{ChatFormActionRecord.svelte → ChatFormActions/ChatFormActionRecord.svelte} +0 -0
- /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/chat/ChatSettings/{ParameterSourceIndicator.svelte → ChatSettingsParameterSourceIndicator.svelte} +0 -0
- /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/{ChatErrorDialog.svelte → DialogChatError.svelte} +0 -0
- /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/{ConfirmationDialog.svelte → DialogConfirmation.svelte} +0 -0
- /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/{ConversationTitleUpdateDialog.svelte → DialogConversationTitleUpdate.svelte} +0 -0
- /vendor_llama_cpp_pydist/llama.cpp/tools/server/webui/src/lib/components/app/dialogs/{EmptyFileAlertDialog.svelte → DialogEmptyFileAlert.svelte} +0 -0
|
Binary file
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: llama_cpp_pydist
|
|
3
|
-
Version: 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
|