mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-31 05:03:44 +00:00
8ca4283f55
# Conflicts: # .github/workflows/release.yml # .github/workflows/server.yml # .github/workflows/ui-build.yml # .github/workflows/ui-publish.yml # CMakeLists.txt # docs/autoparser.md # docs/backend/snapdragon/CMakeUserPresets.json # docs/backend/snapdragon/README.md # docs/backend/snapdragon/windows.md # docs/function-calling.md # examples/model-conversion/scripts/embedding/run-original-model.py # ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c # ggml/src/ggml-opencl/ggml-opencl.cpp # ggml/src/ggml-opencl/kernels/cvt.cl # ggml/src/ggml-opencl/kernels/gemm_moe_mxfp4_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemm_moe_q4_0_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemm_moe_q4_1_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemm_moe_q4_k_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemm_moe_q5_0_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemm_moe_q5_1_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemm_moe_q5_k_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemm_moe_q6_k_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemv_moe_mxfp4_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemv_moe_q4_0_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemv_moe_q4_1_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemv_moe_q4_k_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemv_moe_q5_0_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemv_moe_q5_1_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemv_moe_q5_k_f32_ns.cl # ggml/src/ggml-opencl/kernels/gemv_moe_q6_k_f32_ns.cl # ggml/src/ggml-sycl/common.hpp # ggml/src/ggml-sycl/dmmv.cpp # ggml/src/ggml-sycl/gated_delta_net.cpp # ggml/src/ggml-sycl/ggml-sycl.cpp # ggml/src/ggml-vulkan/CMakeLists.txt # ggml/src/ggml-zendnn/CMakeLists.txt # ggml/src/ggml-zendnn/ggml-zendnn.cpp # requirements/requirements-convert_hf_to_gguf.txt # scripts/snapdragon/windows/setup-build.ps1 # tools/perplexity/perplexity.cpp |
||
|---|---|---|
| .. | ||
| models | ||
| llama-adapter.cpp | ||
| llama-adapter.h | ||
| llama-arch.cpp | ||
| llama-arch.h | ||
| llama-batch.cpp | ||
| llama-batch.h | ||
| llama-chat.cpp | ||
| llama-chat.h | ||
| llama-context.cpp | ||
| llama-context.h | ||
| llama-cparams.cpp | ||
| llama-cparams.h | ||
| llama-ext.h | ||
| llama-grammar.cpp | ||
| llama-grammar.h | ||
| llama-graph.cpp | ||
| llama-graph.h | ||
| llama-hparams.cpp | ||
| llama-hparams.h | ||
| llama-impl.cpp | ||
| llama-impl.h | ||
| llama-io.cpp | ||
| llama-io.h | ||
| llama-kv-cache-iswa.cpp | ||
| llama-kv-cache-iswa.h | ||
| llama-kv-cache.cpp | ||
| llama-kv-cache.h | ||
| llama-kv-cells.h | ||
| llama-memory-hybrid-iswa.cpp | ||
| llama-memory-hybrid-iswa.h | ||
| llama-memory-hybrid.cpp | ||
| llama-memory-hybrid.h | ||
| llama-memory-recurrent.cpp | ||
| llama-memory-recurrent.h | ||
| llama-memory.cpp | ||
| llama-memory.h | ||
| llama-mmap.cpp | ||
| llama-mmap.h | ||
| llama-model-loader.cpp | ||
| llama-model-loader.h | ||
| llama-model-saver.cpp | ||
| llama-model-saver.h | ||
| llama-model.cpp | ||
| llama-model.h | ||
| llama-quant.cpp | ||
| llama-quant.h | ||
| llama-sampler.cpp | ||
| llama-sampler.h | ||
| llama-vocab.cpp | ||
| llama-vocab.h | ||
| llama.cpp | ||
| unicode-data.cpp | ||
| unicode-data.h | ||
| unicode.cpp | ||
| unicode.h | ||