llmnpc - llama.cpp/Makefile

archive

llama.cpp-b8008.tar.gz

corpus

lotr.txt map1_bromm.txt map1_dagna.txt map1_keldor.txt map1_skara.txt map1_thrain.txt

.devops

nix

apps.nix devshells.nix docker.nix jetson-support.nix nixpkgs-instances.nix package-gguf-py.nix package.nix python-scripts.nix scope.nix sif.nix

cann.Dockerfile cpu.Dockerfile cuda-new.Dockerfile cuda.Dockerfile intel.Dockerfile llama-cli-cann.Dockerfile llama-cpp-cuda.srpm.spec llama-cpp.srpm.spec musa.Dockerfile rocm.Dockerfile s390x.Dockerfile tools.sh vulkan.Dockerfile

.gemini

.github

010-bug-compilation.yml 011-bug-results.yml 019-bug-misc.yml 020-enhancement.yml 030-research.yml 040-refactor.yml config.yml

actions

action.yml

action.yml

linux-setup-spacemit

action.yml

linux-setup-vulkan

action.yml

action.yml

windows-setup-cuda

action.yml

windows-setup-rocm

action.yml

bench.yml.disabled build-cache.yml build-cmake-pkg.yml build-linux-cross.yml build.yml check-vendor.yml close-issue.yml copilot-setup-steps.yml docker.yml editorconfig.yml gguf-publish.yml labeler.yml pre-tokenizer-hashes.yml python-check-requirements.yml python-lint.yml python-type-check.yml release.yml server-metal.yml server-webui.yml server.yml update-ops-docs.yml winget.yml

labeler.yml pull_request_template.md

benches

aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547.html aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547.json aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547_allresults.json dgx-spark.md

mac-m2-ultra.md

ci

README-MUSA.md README.md run.sh

cmake

arm64-apple-clang.cmake arm64-windows-llvm.cmake build-info.cmake common.cmake download-models.cmake git-vars.cmake license.cmake llama-config.cmake.in llama.pc.in riscv64-spacemit-linux-gnu-gcc.cmake x64-windows-llvm.cmake

common

jinja

README.md caps.cpp caps.h lexer.cpp lexer.h parser.cpp parser.h runtime.cpp runtime.h string.cpp string.h utils.h value.cpp value.h

CMakeLists.txt arg.cpp arg.h base64.hpp build-info.cpp.in chat-parser-xml-toolcall.cpp chat-parser-xml-toolcall.h chat-parser.cpp chat-parser.h chat-peg-parser.cpp chat-peg-parser.h chat.cpp chat.h common.cpp common.h console.cpp console.h debug.cpp debug.h download.cpp download.h http.h json-partial.cpp json-partial.h json-schema-to-grammar.cpp json-schema-to-grammar.h llguidance.cpp log.cpp log.h ngram-cache.cpp ngram-cache.h ngram-map.cpp ngram-map.h ngram-mod.cpp ngram-mod.h peg-parser.cpp peg-parser.h preset.cpp preset.h regex-partial.cpp regex-partial.h sampling.cpp sampling.h speculative.cpp speculative.h unicode.cpp unicode.h

docs

android

imported-into-android-studio.jpg

backend

VirtGPU

configuration.md development.md

CMakeUserPresets.json README.md developer.md windows.md

BLIS.md CANN.md CUDA-FEDORA.md OPENCL.md SYCL.md VirtGPU.md ZenDNN.md zDNN.md

idea-arch.key idea-arch.pdf

HOWTO-add-model.md debugging-tests.md parsing.md token_generation_performance_tips.md

MobileVLM.md gemma3.md glmedge.md granitevision.md llava.md minicpmo2.6.md minicpmo4.0.md minicpmv2.5.md minicpmv2.6.md minicpmv4.0.md minicpmv4.5.md

ops

BLAS.csv CANN.csv CPU.csv CUDA.csv Metal.csv OpenCL.csv SYCL.csv Vulkan.csv WebGPU.csv ZenDNN.csv zDNN.csv

android.md build-riscv64-spacemit.md build-s390x.md build.md docker.md function-calling.md install.md llguidance.md multimodal.md ops.md preset.md speculative.md

examples

batched

CMakeLists.txt README.md batched.cpp

Sources

main.swift

.gitignore Makefile Package.swift README.md

convert-llama2c-to-ggml

CMakeLists.txt README.md convert-llama2c-to-ggml.cpp

debug

CMakeLists.txt README.md debug.cpp

deprecation-warning

README.md deprecation-warning.cpp

CMakeLists.txt README.md diffusion-cli.cpp

CMakeLists.txt README.md embedding.cpp

CMakeLists.txt README.md eval-callback.cpp

gen-docs

CMakeLists.txt gen-docs.cpp

gguf

CMakeLists.txt gguf.cpp

deps

package.json rotate-bits.h

sha1

package.json sha1.c sha1.h

sha256

package.json sha256.c sha256.h

xxhash

clib.json xxhash.c xxhash.h

CMakeLists.txt README.md gguf-hash.cpp

idle

CMakeLists.txt README.md idle.cpp

app

src

main

java

com

example

llama

MainActivity.kt MessageAdapter.kt

res

drawable

bg_assistant_message.xml bg_user_message.xml ic_launcher_background.xml ic_launcher_foreground.xml outline_folder_open_24.xml outline_send_24.xml

layout

activity_main.xml item_message_assistant.xml item_message_user.xml

ic_launcher.xml ic_launcher_round.xml

ic_launcher.webp ic_launcher_round.webp

ic_launcher.webp ic_launcher_round.webp

ic_launcher.webp ic_launcher_round.webp

ic_launcher.webp ic_launcher_round.webp

ic_launcher.webp ic_launcher_round.webp

values

colors.xml strings.xml themes.xml

xml

backup_rules.xml data_extraction_rules.xml

AndroidManifest.xml

.gitignore build.gradle.kts proguard-rules.pro

gradle

wrapper

gradle-wrapper.jar gradle-wrapper.properties

libs.versions.toml

lib

src

java

android

llama

cpp

ExampleInstrumentedTest.kt

main

cpp

CMakeLists.txt ai_chat.cpp logging.h

java

com

arm

aichat

gguf

FileType.kt GgufMetadata.kt GgufMetadataReader.kt

internal

gguf

GgufMetadataReaderImpl.kt

InferenceEngineImpl.kt

AiChat.kt InferenceEngine.kt

AndroidManifest.xml

test

java

android

llama

cpp

ExampleUnitTest.kt

.gitignore build.gradle.kts consumer-rules.pro proguard-rules.pro

.gitignore build.gradle.kts gradle.properties gradlew settings.gradle.kts

llama.cpp.swift

Assets.xcassets

AppIcon.appiconset

Models

LlamaState.swift

models

.gitignore

UI

ContentView.swift DownloadButton.swift InputButton.swift LoadCustomButton.swift

llama_swiftuiApp.swift

llama.swiftui.xcodeproj

project.xcworkspace

contents.xcworkspacedata

project.pbxproj

.gitignore README.md

CMakeLists.txt README.md lookahead.cpp

lookup

CMakeLists.txt README.md lookup-create.cpp lookup-merge.cpp lookup-stats.cpp lookup.cpp

model-conversion

scripts

causal

compare-embeddings-logits.sh compare-logits.py convert-model.sh modelcard.template run-casual-gen-embeddings-org.py run-converted-model-embeddings-logits.sh run-converted-model.sh run-org-model.py

compare-embeddings-logits.sh convert-model.sh modelcard.template run-converted-model.sh run-original-model.py

utils

__init__.py check-nmse.py common.py compare_tokens.py create-collection-add-model.sh curl-embedding-server.sh hf-add-model-to-collection.py hf-create-collection.py hf-create-model.py hf-upload-gguf-model.py inspect-converted-model.sh inspect-org-model.py perplexity-gen.sh perplexity-run-simple.sh perplexity-run.sh quantize.sh run-embedding-server.sh semantic_check.py tensor-info.py

.gitignore Makefile README.md requirements.txt

parallel

CMakeLists.txt README.md parallel.cpp

passkey

CMakeLists.txt README.md passkey.cpp

CMakeLists.txt README.md retrieval.cpp

save-load-state

CMakeLists.txt save-load-state.cpp

simple

CMakeLists.txt README.md simple.cpp

CMakeLists.txt README.md simple-chat.cpp

simple-cmake-pkg

.gitignore CMakeLists.txt README.md

CMakeLists.txt README.md speculative.cpp

speculative-simple

CMakeLists.txt README.md speculative-simple.cpp

sycl

CMakeLists.txt README.md build.sh ls-sycl-device.cpp run-llama2.sh test.sh win-build-sycl.bat win-run-llama2.bat win-test.bat

training

CMakeLists.txt README.md finetune.cpp

CMakeLists.txt convert_legacy_llama.py json_schema_pydantic_example.py json_schema_to_grammar.py llama.vim pydantic_models_to_grammar.py pydantic_models_to_grammar_examples.py reason-act.sh regex_to_grammar.py server-llama2-13B.sh server_embd.py ts-type-to-grammar.sh

ggml

cmake

GitVars.cmake common.cmake ggml-config.cmake.in

include

ggml-alloc.h ggml-backend.h ggml-blas.h ggml-cann.h ggml-cpp.h ggml-cpu.h ggml-cuda.h ggml-hexagon.h ggml-metal.h ggml-opencl.h ggml-opt.h ggml-rpc.h ggml-sycl.h ggml-virtgpu.h ggml-vulkan.h ggml-webgpu.h ggml-zdnn.h ggml-zendnn.h ggml.h gguf.h

src

CMakeLists.txt ggml-blas.cpp

CMakeLists.txt acl_tensor.cpp acl_tensor.h aclnn_ops.cpp aclnn_ops.h common.h ggml-cann.cpp

ggml-cpu

amx

amx.cpp amx.h common.h mmq.cpp mmq.h

arch

arm

cpu-feats.cpp quants.c repack.cpp

quants.c

powerpc

cpu-feats.cpp quants.c

riscv

cpu-feats.cpp quants.c repack.cpp

s390

cpu-feats.cpp quants.c

wasm

quants.c

x86

cpu-feats.cpp quants.c repack.cpp

cmake

kleidiai

kernels.cpp kernels.h kleidiai.cpp kleidiai.h

sgemm-ppc.h sgemm.cpp sgemm.h

spacemit

ime.cpp ime.h ime1_kernels.cpp ime_kernels.h

CMakeLists.txt arch-fallback.h binary-ops.cpp binary-ops.h common.h ggml-cpu-impl.h ggml-cpu.c ggml-cpu.cpp hbm.cpp hbm.h ops.cpp ops.h quants.c quants.h repack.cpp repack.h simd-mappings.h traits.cpp traits.h unary-ops.cpp unary-ops.h vec.cpp vec.h

template-instances

fattn-mma-f16-instance-ncols1_1-ncols2_16.cu fattn-mma-f16-instance-ncols1_1-ncols2_32.cu fattn-mma-f16-instance-ncols1_1-ncols2_8.cu fattn-mma-f16-instance-ncols1_16-ncols2_1.cu fattn-mma-f16-instance-ncols1_16-ncols2_2.cu fattn-mma-f16-instance-ncols1_16-ncols2_4.cu fattn-mma-f16-instance-ncols1_2-ncols2_16.cu fattn-mma-f16-instance-ncols1_2-ncols2_32.cu fattn-mma-f16-instance-ncols1_2-ncols2_4.cu fattn-mma-f16-instance-ncols1_2-ncols2_8.cu fattn-mma-f16-instance-ncols1_32-ncols2_1.cu fattn-mma-f16-instance-ncols1_32-ncols2_2.cu fattn-mma-f16-instance-ncols1_4-ncols2_16.cu fattn-mma-f16-instance-ncols1_4-ncols2_2.cu fattn-mma-f16-instance-ncols1_4-ncols2_4.cu fattn-mma-f16-instance-ncols1_4-ncols2_8.cu fattn-mma-f16-instance-ncols1_64-ncols2_1.cu fattn-mma-f16-instance-ncols1_8-ncols2_1.cu fattn-mma-f16-instance-ncols1_8-ncols2_2.cu fattn-mma-f16-instance-ncols1_8-ncols2_4.cu fattn-mma-f16-instance-ncols1_8-ncols2_8.cu fattn-tile-instance-dkq112-dv112.cu fattn-tile-instance-dkq128-dv128.cu fattn-tile-instance-dkq256-dv256.cu fattn-tile-instance-dkq40-dv40.cu fattn-tile-instance-dkq576-dv512.cu fattn-tile-instance-dkq64-dv64.cu fattn-tile-instance-dkq72-dv72.cu fattn-tile-instance-dkq80-dv80.cu fattn-tile-instance-dkq96-dv96.cu fattn-vec-instance-f16-f16.cu fattn-vec-instance-f16-q4_0.cu fattn-vec-instance-f16-q4_1.cu fattn-vec-instance-f16-q5_0.cu fattn-vec-instance-f16-q5_1.cu fattn-vec-instance-f16-q8_0.cu fattn-vec-instance-q4_0-f16.cu fattn-vec-instance-q4_0-q4_0.cu fattn-vec-instance-q4_0-q4_1.cu fattn-vec-instance-q4_0-q5_0.cu fattn-vec-instance-q4_0-q5_1.cu fattn-vec-instance-q4_0-q8_0.cu fattn-vec-instance-q4_1-f16.cu fattn-vec-instance-q4_1-q4_0.cu fattn-vec-instance-q4_1-q4_1.cu fattn-vec-instance-q4_1-q5_0.cu fattn-vec-instance-q4_1-q5_1.cu fattn-vec-instance-q4_1-q8_0.cu fattn-vec-instance-q5_0-f16.cu fattn-vec-instance-q5_0-q4_0.cu fattn-vec-instance-q5_0-q4_1.cu fattn-vec-instance-q5_0-q5_0.cu fattn-vec-instance-q5_0-q5_1.cu fattn-vec-instance-q5_0-q8_0.cu fattn-vec-instance-q5_1-f16.cu fattn-vec-instance-q5_1-q4_0.cu fattn-vec-instance-q5_1-q4_1.cu fattn-vec-instance-q5_1-q5_0.cu fattn-vec-instance-q5_1-q5_1.cu fattn-vec-instance-q5_1-q8_0.cu fattn-vec-instance-q8_0-f16.cu fattn-vec-instance-q8_0-q4_0.cu fattn-vec-instance-q8_0-q4_1.cu fattn-vec-instance-q8_0-q5_0.cu fattn-vec-instance-q8_0-q5_1.cu fattn-vec-instance-q8_0-q8_0.cu generate_cu_files.py mmf-instance-ncols_1.cu mmf-instance-ncols_10.cu mmf-instance-ncols_11.cu mmf-instance-ncols_12.cu mmf-instance-ncols_13.cu mmf-instance-ncols_14.cu mmf-instance-ncols_15.cu mmf-instance-ncols_16.cu mmf-instance-ncols_2.cu mmf-instance-ncols_3.cu mmf-instance-ncols_4.cu mmf-instance-ncols_5.cu mmf-instance-ncols_6.cu mmf-instance-ncols_7.cu mmf-instance-ncols_8.cu mmf-instance-ncols_9.cu mmq-instance-iq1_s.cu mmq-instance-iq2_s.cu mmq-instance-iq2_xs.cu mmq-instance-iq2_xxs.cu mmq-instance-iq3_s.cu mmq-instance-iq3_xxs.cu mmq-instance-iq4_nl.cu mmq-instance-iq4_xs.cu mmq-instance-mxfp4.cu mmq-instance-q2_k.cu mmq-instance-q3_k.cu mmq-instance-q4_0.cu mmq-instance-q4_1.cu mmq-instance-q4_k.cu mmq-instance-q5_0.cu mmq-instance-q5_1.cu mmq-instance-q5_k.cu mmq-instance-q6_k.cu mmq-instance-q8_0.cu

vendors

cuda.h hip.h musa.h

CMakeLists.txt acc.cu acc.cuh add-id.cu add-id.cuh arange.cu arange.cuh argmax.cu argmax.cuh argsort.cu argsort.cuh binbcast.cu binbcast.cuh clamp.cu clamp.cuh common.cuh concat.cu concat.cuh conv-transpose-1d.cu conv-transpose-1d.cuh conv2d-dw.cu conv2d-dw.cuh conv2d-transpose.cu conv2d-transpose.cuh conv2d.cu conv2d.cuh convert.cu convert.cuh count-equal.cu count-equal.cuh cp-async.cuh cpy-utils.cuh cpy.cu cpy.cuh cross-entropy-loss.cu cross-entropy-loss.cuh cumsum.cu cumsum.cuh dequantize.cuh diag.cu diag.cuh diagmask.cu diagmask.cuh fattn-common.cuh fattn-mma-f16.cuh fattn-tile.cu fattn-tile.cuh fattn-vec.cuh fattn-wmma-f16.cu fattn-wmma-f16.cuh fattn.cu fattn.cuh fill.cu fill.cuh getrows.cu getrows.cuh ggml-cuda.cu gla.cu gla.cuh im2col.cu im2col.cuh mean.cu mean.cuh mma.cuh mmf.cu mmf.cuh mmid.cu mmid.cuh mmq.cu mmq.cuh mmvf.cu mmvf.cuh mmvq.cu mmvq.cuh norm.cu norm.cuh opt-step-adamw.cu opt-step-adamw.cuh opt-step-sgd.cu opt-step-sgd.cuh out-prod.cu out-prod.cuh pad.cu pad.cuh pad_reflect_1d.cu pad_reflect_1d.cuh pool2d.cu pool2d.cuh quantize.cu quantize.cuh reduce_rows.cuh roll.cu roll.cuh rope.cu rope.cuh scale.cu scale.cuh set-rows.cu set-rows.cuh set.cu set.cuh softcap.cu softcap.cuh softmax.cu softmax.cuh solve_tri.cu solve_tri.cuh ssm-conv.cu ssm-conv.cuh ssm-scan.cu ssm-scan.cuh sum.cu sum.cuh sumrows.cu sumrows.cuh top-k.cu top-k.cuh topk-moe.cu topk-moe.cuh tri.cu tri.cuh tsembd.cu tsembd.cuh unary.cu unary.cuh upscale.cu upscale.cuh vecdotq.cuh wkv.cu wkv.cuh

htp

CMakeLists.txt act-ops.c argsort-ops.c binary-ops.c cmake-toolchain.cmake cpy-ops.c flash-attn-ops.c get-rows-ops.c hex-dma.c hex-dma.h hex-dump.h hex-fastdiv.h hex-utils.h htp-ctx.h htp-msg.h htp-ops.h htp_iface.idl hvx-arith.h hvx-base.h hvx-copy.h hvx-div.h hvx-dump.h hvx-exp.h hvx-floor.h hvx-inverse.h hvx-reduce.h hvx-scale.h hvx-sigmoid.h hvx-sqrt.h hvx-types.h hvx-utils.h main.c matmul-ops.c rope-ops.c set-rows-ops.c softmax-ops.c sum-rows-ops.c unary-ops.c worker-pool.c worker-pool.h

CMakeLists.txt ggml-hexagon.cpp htp-drv.cpp htp-drv.h libdl.h libggml-htp.inf op-desc.h

ggml-hip

CMakeLists.txt ggml-metal-common.cpp ggml-metal-common.h ggml-metal-context.h ggml-metal-context.m ggml-metal-device.cpp ggml-metal-device.h ggml-metal-device.m ggml-metal-impl.h ggml-metal-ops.cpp ggml-metal-ops.h ggml-metal.cpp ggml-metal.metal

CMakeLists.txt mudnn.cu mudnn.cuh

kernels

add.cl add_id.cl argsort.cl clamp.cl concat.cl conv2d.cl conv2d_f16_f32.cl cpy.cl cvt.cl diag_mask_inf.cl div.cl embed_kernel.py expm1.cl fill.cl flash_attn_f16.cl flash_attn_f32.cl flash_attn_f32_f16.cl gelu.cl gemm_moe_mxfp4_f32.cl gemv_moe_mxfp4_f32.cl gemv_noshuffle.cl gemv_noshuffle_general.cl gemv_noshuffle_general_q8_0_f32.cl get_rows.cl glu.cl group_norm.cl im2col_f16.cl im2col_f32.cl mean.cl mul.cl mul_mat_Ab_Bi_8x4.cl mul_mat_f16_f32.cl mul_mm_f16_f32_kq_kqv.cl mul_mm_f16_f32_l4_lm.cl mul_mm_f32_f32_l4_lm.cl mul_mm_q6_k_f32_l4_lm.cl mul_mm_q8_0_f32_8x4.cl mul_mm_q8_0_f32_l4_lm.cl mul_mv_f16_f16.cl mul_mv_f16_f32.cl mul_mv_f16_f32_1row.cl mul_mv_f16_f32_l4.cl mul_mv_f32_f32.cl mul_mv_id_mxfp4_f32.cl mul_mv_id_mxfp4_f32_flat.cl mul_mv_id_q4_0_f32_8x_flat.cl mul_mv_id_q8_0_f32.cl mul_mv_id_q8_0_f32_flat.cl mul_mv_mxfp4_f32.cl mul_mv_mxfp4_f32_flat.cl mul_mv_q4_0_f32.cl mul_mv_q4_0_f32_1d_16x_flat.cl mul_mv_q4_0_f32_1d_8x_flat.cl mul_mv_q4_0_f32_8x_flat.cl mul_mv_q4_0_f32_v.cl mul_mv_q4_k_f32.cl mul_mv_q6_k_f32.cl mul_mv_q6_k_f32_flat.cl mul_mv_q8_0_f32.cl mul_mv_q8_0_f32_flat.cl norm.cl pad.cl relu.cl repeat.cl rms_norm.cl rope.cl scale.cl set_rows.cl sigmoid.cl silu.cl softmax_4_f16.cl softmax_4_f32.cl softmax_f16.cl softmax_f32.cl softplus.cl solve_tri.cl sqr.cl sqrt.cl ssm_conv.cl sub.cl sum_rows.cl tanh.cl transpose.cl tri.cl tsembd.cl upscale.cl

CMakeLists.txt ggml-opencl.cpp

ggml-rpc

CMakeLists.txt ggml-rpc.cpp

dpct

helper.hpp

CMakeLists.txt add-id.cpp add-id.hpp backend.hpp binbcast.cpp binbcast.hpp common.cpp common.hpp concat.cpp concat.hpp conv.cpp conv.hpp convert.cpp convert.hpp count-equal.cpp count-equal.hpp cpy.cpp cpy.hpp dequantize.hpp dmmv.cpp dmmv.hpp element_wise.cpp element_wise.hpp gemm.hpp getrows.cpp getrows.hpp ggml-sycl.cpp gla.cpp gla.hpp im2col.cpp im2col.hpp mmq.cpp mmq.hpp mmvq.cpp mmvq.hpp norm.cpp norm.hpp outprod.cpp outprod.hpp pad.cpp pad.hpp pad_reflect_1d.cpp pad_reflect_1d.hpp presets.hpp quantize.hpp quants.hpp repeat_back.cpp repeat_back.hpp roll.cpp roll.hpp rope.cpp rope.hpp set.cpp set.hpp set_rows.cpp set_rows.hpp softmax.cpp softmax.hpp ssm_conv.cpp ssm_conv.hpp sycl_hw.cpp sycl_hw.hpp tsembd.cpp tsembd.hpp vecdotq.hpp wkv.cpp wkv.hpp

backend

shared

api_remoting.h apir_backend.gen.h apir_backend.h apir_cs.h apir_cs_ggml.h apir_cs_rpc.h

CMakeLists.txt apir_cs_ggml-rpc-back.cpp backend-convert.h backend-dispatched-backend.cpp backend-dispatched-buffer-type.cpp backend-dispatched-buffer.cpp backend-dispatched-device.cpp backend-dispatched.cpp backend-dispatched.gen.h backend-dispatched.h backend-virgl-apir.h backend.cpp

include

apir_hw.h

CMakeLists.txt apir_cs_ggml-rpc-front.cpp ggml-backend-buffer-type.cpp ggml-backend-buffer.cpp ggml-backend-device.cpp ggml-backend-reg.cpp ggml-backend.cpp ggml-remoting.h ggmlremoting_functions.yaml regenerate_remoting.py virtgpu-apir.h virtgpu-forward-backend.cpp virtgpu-forward-buffer-type.cpp virtgpu-forward-buffer.cpp virtgpu-forward-device.cpp virtgpu-forward-impl.h virtgpu-forward.gen.h virtgpu-shm.cpp virtgpu-shm.h virtgpu-utils.cpp virtgpu-utils.h virtgpu.cpp virtgpu.h

cmake

host-toolchain.cmake.in

bfloat16.comp coopmat.comp coopmat2.comp integer_dot.comp

CMakeLists.txt abs.comp acc.comp add.comp add1.comp add_id.comp arange.comp argmax.comp argsort.comp argsort_large.comp ceil.comp clamp.comp concat.comp contig_copy.comp conv2d_dw.comp conv2d_mm.comp conv_transpose_1d.comp copy.comp copy_from_quant.comp copy_to_quant.comp copy_transpose.comp cos.comp count_equal.comp count_experts.comp cumsum.comp cumsum_multipass1.comp cumsum_multipass2.comp dequant_f32.comp dequant_funcs.glsl dequant_funcs_cm2.glsl dequant_head.glsl dequant_iq1_m.comp dequant_iq1_s.comp dequant_iq2_s.comp dequant_iq2_xs.comp dequant_iq2_xxs.comp dequant_iq3_s.comp dequant_iq3_xxs.comp dequant_iq4_nl.comp dequant_iq4_xs.comp dequant_mxfp4.comp dequant_q2_k.comp dequant_q3_k.comp dequant_q4_0.comp dequant_q4_1.comp dequant_q4_k.comp dequant_q5_0.comp dequant_q5_1.comp dequant_q5_k.comp dequant_q6_k.comp dequant_q8_0.comp diag.comp diag_mask_inf.comp div.comp exp.comp fill.comp flash_attn.comp flash_attn_base.glsl flash_attn_cm1.comp flash_attn_cm2.comp flash_attn_mask_opt.comp flash_attn_split_k_reduce.comp floor.comp geglu.comp geglu_erf.comp geglu_quick.comp gelu.comp gelu_erf.comp gelu_quick.comp generic_binary_head.glsl generic_head.glsl generic_unary_head.glsl get_rows.comp get_rows_quant.comp glu_head.glsl glu_main.glsl group_norm.comp hardsigmoid.comp hardswish.comp im2col.comp im2col_3d.comp l2_norm.comp leaky_relu.comp log.comp mul.comp mul_mat_split_k_reduce.comp mul_mat_vec.comp mul_mat_vec_base.glsl mul_mat_vec_iface.glsl mul_mat_vec_iq1_m.comp mul_mat_vec_iq1_s.comp mul_mat_vec_iq2_s.comp mul_mat_vec_iq2_xs.comp mul_mat_vec_iq2_xxs.comp mul_mat_vec_iq3_s.comp mul_mat_vec_iq3_xxs.comp mul_mat_vec_nc.comp mul_mat_vec_p021.comp mul_mat_vec_q2_k.comp mul_mat_vec_q3_k.comp mul_mat_vec_q4_k.comp mul_mat_vec_q5_k.comp mul_mat_vec_q6_k.comp mul_mat_vecq.comp mul_mat_vecq_funcs.glsl mul_mm.comp mul_mm_cm2.comp mul_mm_funcs.glsl mul_mm_id_funcs.glsl mul_mmq.comp mul_mmq_funcs.glsl mul_mmq_shmem_types.glsl multi_add.comp neg.comp norm.comp opt_step_adamw.comp opt_step_sgd.comp pad.comp pool2d.comp quantize_q8_1.comp reglu.comp relu.comp repeat.comp repeat_back.comp rms_norm.comp rms_norm_back.comp rms_norm_partials.comp roll.comp rope_funcs.glsl rope_head.glsl rope_multi.comp rope_neox.comp rope_norm.comp rope_params.glsl rope_vision.comp round.comp rte.glsl scale.comp sigmoid.comp silu.comp silu_back.comp sin.comp soft_max.comp soft_max_back.comp soft_max_large1.comp soft_max_large2.comp soft_max_large3.comp soft_max_large_common.glsl softplus.comp solve_tri.comp sqrt.comp square.comp ssm_conv.comp ssm_scan.comp step.comp sub.comp sum_rows.comp sum_rows.glsl swiglu.comp swiglu_oai.comp tanh.comp timestep_embedding.comp topk_argsort.comp topk_moe.comp topk_nary_search.comp tri.comp trunc.comp types.glsl upscale.comp utils.glsl vulkan-shaders-gen.cpp wkv6.comp wkv7.comp xielu.comp

CMakeLists.txt ggml-vulkan.cpp

argmax.wgsl argsort.wgsl argsort_merge.wgsl binary.wgsl common_decls.tmpl cpy.tmpl.wgsl cumsum.wgsl embed_wgsl.py flash_attn.wgsl get_rows.tmpl.wgsl glu.tmpl.wgsl memset.wgsl mul_mat.tmpl.wgsl mul_mat_decls.tmpl mul_mat_reg_tile.tmpl.wgsl mul_mat_subgroup_matrix.tmpl.wgsl mul_mat_vec.tmpl.wgsl pad.wgsl rms_norm.wgsl rope.tmpl.wgsl scale.tmpl.wgsl set_rows.wgsl soft_max.tmpl.wgsl sum_rows.wgsl unary.wgsl

CMakeLists.txt ggml-webgpu-shader-lib.hpp ggml-webgpu.cpp pre_wgsl.hpp

.gitignore CMakeLists.txt common.hpp ggml-zdnn.cpp mmf.cpp mmf.hpp utils.cpp utils.hpp

CMakeLists.txt ggml-zendnn.cpp

CMakeLists.txt ggml-alloc.c ggml-backend-dl.cpp ggml-backend-dl.h ggml-backend-impl.h ggml-backend-reg.cpp ggml-backend.cpp ggml-common.h ggml-impl.h ggml-opt.cpp ggml-quants.c ggml-quants.h ggml-threading.cpp ggml-threading.h ggml.c ggml.cpp gguf.cpp

.gitignore CMakeLists.txt

gguf-py

examples

reader.py writer.py

gguf

scripts

gguf_convert_endian.py gguf_dump.py gguf_editor_gui.py gguf_hash.py gguf_new_metadata.py gguf_set_metadata.py

__init__.py constants.py gguf.py gguf_reader.py gguf_writer.py lazy.py metadata.py py.typed quants.py tensor_mapping.py utility.py vocab.py

tests

__init__.py test_metadata.py test_quants.py

LICENSE README.md pyproject.toml

grammars

README.md arithmetic.gbnf c.gbnf chess.gbnf english.gbnf japanese.gbnf json.gbnf json_arr.gbnf list.gbnf

include

llama-cpp.h llama.h

licenses

LICENSE-jsonhpp

media

llama0-banner.png llama0-logo.png llama1-banner.png llama1-icon-transparent.png llama1-icon-transparent.svg llama1-icon.png llama1-icon.svg llama1-logo.png llama1-logo.svg matmul.png matmul.svg

models

Apertus-8B-Instruct.jinja ByteDance-Seed-OSS.jinja CohereForAI-c4ai-command-r-plus-tool_use.jinja CohereForAI-c4ai-command-r7b-12-2024-tool_use.jinja GLM-4.6.jinja Kimi-K2-Instruct.jinja Kimi-K2-Thinking.jinja MiMo-VL.jinja MiniMax-M2.jinja Mistral-Small-3.2-24B-Instruct-2506.jinja NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.jinja NVIDIA-Nemotron-Nano-v2.jinja NousResearch-Hermes-2-Pro-Llama-3-8B-tool_use.jinja NousResearch-Hermes-3-Llama-3.1-8B-tool_use.jinja Qwen-QwQ-32B.jinja Qwen-Qwen2.5-7B-Instruct.jinja Qwen-Qwen3-0.6B.jinja Qwen3-Coder.jinja README.md deepseek-ai-DeepSeek-R1-Distill-Llama-8B.jinja deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja deepseek-ai-DeepSeek-V3.1.jinja fireworks-ai-llama-3-firefunction-v2.jinja google-gemma-2-2b-it.jinja ibm-granite-granite-3.3-2B-Instruct.jinja llama-cpp-deepseek-r1.jinja llama-cpp-lfm2.jinja llama-cpp-rwkv-world.jinja meetkai-functionary-medium-v3.1.jinja meetkai-functionary-medium-v3.2.jinja meta-llama-Llama-3.1-8B-Instruct.jinja meta-llama-Llama-3.2-3B-Instruct.jinja meta-llama-Llama-3.3-70B-Instruct.jinja microsoft-Phi-3.5-mini-instruct.jinja mistralai-Ministral-3-14B-Reasoning-2512.jinja mistralai-Mistral-Nemo-Instruct-2407.jinja moonshotai-Kimi-K2.jinja openai-gpt-oss-120b.jinja unsloth-Apriel-1.5.jinja unsloth-mistral-Devstral-Small-2507.jinja upstage-Solar-Open-100B.jinja

.editorconfig ggml-vocab-aquila.gguf ggml-vocab-baichuan.gguf ggml-vocab-bert-bge.gguf ggml-vocab-bert-bge.gguf.inp ggml-vocab-bert-bge.gguf.out ggml-vocab-command-r.gguf ggml-vocab-command-r.gguf.inp ggml-vocab-command-r.gguf.out ggml-vocab-deepseek-coder.gguf ggml-vocab-deepseek-coder.gguf.inp ggml-vocab-deepseek-coder.gguf.out ggml-vocab-deepseek-llm.gguf ggml-vocab-deepseek-llm.gguf.inp ggml-vocab-deepseek-llm.gguf.out ggml-vocab-falcon.gguf ggml-vocab-falcon.gguf.inp ggml-vocab-falcon.gguf.out ggml-vocab-gpt-2.gguf ggml-vocab-gpt-2.gguf.inp ggml-vocab-gpt-2.gguf.out ggml-vocab-gpt-neox.gguf ggml-vocab-llama-bpe.gguf ggml-vocab-llama-bpe.gguf.inp ggml-vocab-llama-bpe.gguf.out ggml-vocab-llama-spm.gguf ggml-vocab-llama-spm.gguf.inp ggml-vocab-llama-spm.gguf.out ggml-vocab-mpt.gguf ggml-vocab-mpt.gguf.inp ggml-vocab-mpt.gguf.out ggml-vocab-nomic-bert-moe.gguf ggml-vocab-phi-3.gguf ggml-vocab-phi-3.gguf.inp ggml-vocab-phi-3.gguf.out ggml-vocab-qwen2.gguf ggml-vocab-qwen2.gguf.inp ggml-vocab-qwen2.gguf.out ggml-vocab-refact.gguf ggml-vocab-refact.gguf.inp ggml-vocab-refact.gguf.out ggml-vocab-starcoder.gguf ggml-vocab-starcoder.gguf.inp ggml-vocab-starcoder.gguf.out

pocs

vdot

CMakeLists.txt q8dot.cpp vdot.cpp

requirements-all.txt requirements-compare-llama-bench.txt requirements-convert_hf_to_gguf.txt requirements-convert_hf_to_gguf_update.txt requirements-convert_legacy_llama.txt requirements-convert_llama_ggml_to_gguf.txt requirements-convert_lora_to_gguf.txt requirements-gguf_editor_gui.txt requirements-pydantic.txt requirements-server-bench.txt requirements-test-tokenizer-random.txt requirements-tool_bench.txt

scripts

apple

validate-apps.sh validate-ios.sh validate-macos.sh validate-tvos.sh validate-visionos.sh

jinja

jinja-tester.py requirements.txt

adb

llama-cli.farf run-bench.sh run-cli.sh run-completion.sh run-mtmd.sh run-tool.sh

qdc

tests

readme.md requirements.txt

windows

run-bench.ps1 run-cli.ps1 run-tool.ps1 setup-build.ps1

bench-models.sh build-info.sh check-requirements.sh compare-commits.sh compare-llama-bench.py compare-logprobs.py create_ops_docs.py debug-test.sh fetch_server_test_models.py gen-authors.sh gen-unicode-data.py get-flags.mk get-hellaswag.sh get-pg.sh get-wikitext-103.sh get-wikitext-2.sh get-winogrande.sh get_chat_template.py hf.sh install-oneapi.bat pr2wt.sh serve-static.js server-bench.py sync-ggml-am.sh sync-ggml.last sync-ggml.sh sync_vendor.py tool_bench.py tool_bench.sh verify-checksum-models.py xxd.cmake

src

models

afmoe.cpp apertus.cpp arcee.cpp arctic.cpp arwkv7.cpp baichuan.cpp bailingmoe.cpp bailingmoe2.cpp bert.cpp bitnet.cpp bloom.cpp chameleon.cpp chatglm.cpp codeshell.cpp cogvlm.cpp cohere2-iswa.cpp command-r.cpp dbrx.cpp deci.cpp deepseek.cpp deepseek2.cpp dots1.cpp dream.cpp ernie4-5-moe.cpp ernie4-5.cpp exaone-moe.cpp exaone.cpp exaone4.cpp falcon-h1.cpp falcon.cpp gemma-embedding.cpp gemma.cpp gemma2-iswa.cpp gemma3.cpp gemma3n-iswa.cpp glm4-moe.cpp glm4.cpp gpt2.cpp gptneox.cpp granite-hybrid.cpp granite.cpp graph-context-mamba.cpp grok.cpp grovemoe.cpp hunyuan-dense.cpp hunyuan-moe.cpp internlm2.cpp jais.cpp jamba.cpp kimi-linear.cpp lfm2.cpp llada-moe.cpp llada.cpp llama-iswa.cpp llama.cpp maincoder.cpp mamba.cpp mimo2-iswa.cpp minicpm3.cpp minimax-m2.cpp mistral3.cpp models.h modern-bert.cpp mpt.cpp nemotron-h.cpp nemotron.cpp neo-bert.cpp olmo.cpp olmo2.cpp olmoe.cpp openai-moe-iswa.cpp openelm.cpp orion.cpp pangu-embedded.cpp phi2.cpp phi3.cpp plamo.cpp plamo2.cpp plamo3.cpp plm.cpp qwen.cpp qwen2.cpp qwen2moe.cpp qwen2vl.cpp qwen3.cpp qwen35.cpp qwen35moe.cpp qwen3moe.cpp qwen3next.cpp qwen3vl-moe.cpp qwen3vl.cpp refact.cpp rnd1.cpp rwkv6-base.cpp rwkv6.cpp rwkv6qwen2.cpp rwkv7-base.cpp rwkv7.cpp seed-oss.cpp smallthinker.cpp smollm3.cpp stablelm.cpp starcoder.cpp starcoder2.cpp step35-iswa.cpp t5-dec.cpp t5-enc.cpp wavtokenizer-dec.cpp xverse.cpp

CMakeLists.txt 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-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

tests

simple-tokenize.cpp simple-tokenize.h test-basic.cpp test-gbnf-generation.cpp test-json-parser.cpp test-json-serialization.cpp test-unicode.cpp tests.h

.gitignore CMakeLists.txt get-model.cpp get-model.h run-json-schema-to-grammar.mjs test-alloc.cpp test-arg-parser.cpp test-autorelease.cpp test-backend-ops.cpp test-backend-sampler.cpp test-barrier.cpp test-c.c test-chat-parser.cpp test-chat-peg-parser.cpp test-chat-template.cpp test-chat.cpp test-double-float.cpp test-gbnf-validator.cpp test-gguf.cpp test-grammar-integration.cpp test-grammar-llguidance.cpp test-grammar-parser.cpp test-jinja.cpp test-json-partial.cpp test-json-schema-to-grammar.cpp test-llama-grammar.cpp test-log.cpp test-lora-conversion-inference.sh test-model-load-cancel.cpp test-mtmd-c-api.c test-opt.cpp test-peg-parser.cpp test-quantize-fns.cpp test-quantize-perf.cpp test-quantize-stats.cpp test-regex-partial.cpp test-rope.cpp test-sampling.cpp test-state-restore-fragmented.cpp test-thread-safety.cpp test-tokenizer-0.cpp test-tokenizer-0.py test-tokenizer-0.sh test-tokenizer-1-bpe.cpp test-tokenizer-1-spm.cpp test-tokenizer-random.py test-tokenizers-repo.sh testing.h

tools

CMakeLists.txt README.md batched-bench.cpp

cli

CMakeLists.txt README.md cli.cpp

CMakeLists.txt README.md completion.cpp

cvector-generator

CMakeLists.txt README.md completions.txt cvector-generator.cpp mean.hpp negative.txt pca.hpp positive.txt

CMakeLists.txt README.md export-lora.cpp

CMakeLists.txt README.md fit-params.cpp

CMakeLists.txt README.md gguf-split.cpp tests.sh

imatrix

CMakeLists.txt README.md imatrix.cpp

CMakeLists.txt README.md llama-bench.cpp

mtmd

convert_image_encoder_to_gguf.py glmedge-convert-image-encoder-to-gguf.py glmedge-surgery.py llava_surgery.py llava_surgery_v2.py minicpmv-convert-image-encoder-to-gguf.py minicpmv-surgery.py

models

cogvlm.cpp conformer.cpp glm4v.cpp internvl.cpp kimik25.cpp kimivl.cpp llama4.cpp llava.cpp minicpmv.cpp mobilenetv5.cpp models.h pixtral.cpp qwen2vl.cpp qwen3vl.cpp siglip.cpp whisper-enc.cpp youtuvl.cpp

CMakeLists.txt README.md clip-graph.h clip-impl.h clip-model.h clip.cpp clip.h deprecation-warning.cpp mtmd-audio.cpp mtmd-audio.h mtmd-cli.cpp mtmd-helper.cpp mtmd-helper.h mtmd.cpp mtmd.h requirements.txt test-1.jpeg test-2.mp3 tests.sh

CMakeLists.txt README.md perplexity.cpp

quantize

CMakeLists.txt README.md quantize.cpp tests.sh

rpc

CMakeLists.txt README.md rpc-server.cpp

server

bench

README.md bench.py prometheus.yml requirements.txt script.js

public

index.html.gz loading.html

colorthemes.css completion.js favicon.ico index-new.html index.html index.js json-schema-to-grammar.mjs loading.html prompt-formats.js style.css system-prompts.js theme-beeninorder.css theme-ketivah.css theme-mangotango.css theme-playground.css theme-polarnight.css theme-snowstorm.css

public_simplechat

datautils.mjs index.html readme.md simplechat.css simplechat.js simplechat_screens.webp ui.mjs

tests

unit

test_basic.py test_chat_completion.py test_compat_anthropic.py test_compat_oai_responses.py test_completion.py test_ctx_shift.py test_embedding.py test_infill.py test_lora.py test_rerank.py test_router.py test_security.py test_sleep.py test_slot_save.py test_speculative.py test_template.py test_tokenize.py test_tool_call.py test_vision_api.py

.gitignore README.md conftest.py pytest.ini requirements.txt tests.sh utils.py

themes

README.md buttons_top.png favicon.ico index.html

wild

README.md favicon.ico index.html llama_cpp.png llamapattern.png wild.png

README.md

webui

ModeWatcherDecorator.svelte TooltipProviderDecorator.svelte main.ts preview.ts vitest.setup.ts

docs

high-level-architecture-simplified.md high-level-architecture.md

flows

chat-flow.md conversations-flow.md data-flow-simplified-model-mode.md data-flow-simplified-router-mode.md database-flow.md models-flow.md server-flow.md settings-flow.md

scripts

dev.sh install-git-hooks.sh post-build.sh

src

lib

app

chat

ChatAttachments

ChatAttachmentPreview.svelte ChatAttachmentThumbnailFile.svelte ChatAttachmentThumbnailImage.svelte ChatAttachmentsList.svelte ChatAttachmentsViewAll.svelte

ChatForm

ChatFormActions

ChatFormActionFileAttachments.svelte ChatFormActionRecord.svelte ChatFormActionSubmit.svelte ChatFormActions.svelte

ChatForm.svelte ChatFormFileInputInvisible.svelte ChatFormHelperText.svelte ChatFormTextarea.svelte

ChatMessage.svelte ChatMessageActions.svelte ChatMessageAssistant.svelte ChatMessageBranchingControls.svelte ChatMessageEditForm.svelte ChatMessageStatistics.svelte ChatMessageSystem.svelte ChatMessageThinkingBlock.svelte ChatMessageUser.svelte ChatMessages.svelte

ChatScreen.svelte ChatScreenDragOverlay.svelte ChatScreenHeader.svelte ChatScreenProcessingInfo.svelte

ChatSettings.svelte ChatSettingsFields.svelte ChatSettingsFooter.svelte ChatSettingsImportExportTab.svelte ChatSettingsParameterSourceIndicator.svelte

ChatSidebar.svelte ChatSidebarActions.svelte ChatSidebarConversationItem.svelte ChatSidebarSearch.svelte handle-mobile-sidebar-item-click.ts

dialogs

DialogChatAttachmentPreview.svelte DialogChatAttachmentsViewAll.svelte DialogChatError.svelte DialogChatSettings.svelte DialogConfirmation.svelte DialogConversationSelection.svelte DialogConversationTitleUpdate.svelte DialogEmptyFileAlert.svelte DialogModelInformation.svelte DialogModelNotAvailable.svelte

misc

ActionButton.svelte ActionDropdown.svelte BadgeChatStatistic.svelte BadgeInfo.svelte BadgeModality.svelte CodePreviewDialog.svelte ConversationSelection.svelte CopyToClipboardIcon.svelte KeyboardShortcutInfo.svelte MarkdownContent.svelte RemoveButton.svelte SearchInput.svelte SyntaxHighlightedCode.svelte

models

ModelBadge.svelte ModelsSelector.svelte

server

ServerErrorSplash.svelte ServerLoadingSplash.svelte ServerStatus.svelte

index.ts

ui

alert

alert-description.svelte alert-title.svelte alert.svelte index.ts

alert-dialog-action.svelte alert-dialog-cancel.svelte alert-dialog-content.svelte alert-dialog-description.svelte alert-dialog-footer.svelte alert-dialog-header.svelte alert-dialog-overlay.svelte alert-dialog-title.svelte alert-dialog-trigger.svelte index.ts

badge

badge.svelte index.ts

button

button.svelte index.ts

card

card-action.svelte card-content.svelte card-description.svelte card-footer.svelte card-header.svelte card-title.svelte card.svelte index.ts

checkbox

checkbox.svelte index.ts

collapsible-content.svelte collapsible-trigger.svelte collapsible.svelte index.ts

dialog

dialog-close.svelte dialog-content.svelte dialog-description.svelte dialog-footer.svelte dialog-header.svelte dialog-overlay.svelte dialog-title.svelte dialog-trigger.svelte index.ts

dropdown-menu-checkbox-item.svelte dropdown-menu-content.svelte dropdown-menu-group-heading.svelte dropdown-menu-group.svelte dropdown-menu-item.svelte dropdown-menu-label.svelte dropdown-menu-radio-group.svelte dropdown-menu-radio-item.svelte dropdown-menu-separator.svelte dropdown-menu-shortcut.svelte dropdown-menu-sub-content.svelte dropdown-menu-sub-trigger.svelte dropdown-menu-trigger.svelte index.ts

input

index.ts input.svelte

label

index.ts label.svelte

popover

index.ts popover-close.svelte popover-content.svelte popover-portal.svelte popover-trigger.svelte popover.svelte

index.ts scroll-area-scrollbar.svelte scroll-area.svelte

select

index.ts select-content.svelte select-group-heading.svelte select-group.svelte select-item.svelte select-label.svelte select-scroll-down-button.svelte select-scroll-up-button.svelte select-separator.svelte select-trigger.svelte

index.ts separator.svelte

sheet

index.ts sheet-close.svelte sheet-content.svelte sheet-description.svelte sheet-footer.svelte sheet-header.svelte sheet-overlay.svelte sheet-title.svelte sheet-trigger.svelte

sidebar

constants.ts context.svelte.ts index.ts sidebar-content.svelte sidebar-footer.svelte sidebar-group-action.svelte sidebar-group-content.svelte sidebar-group-label.svelte sidebar-group.svelte sidebar-header.svelte sidebar-input.svelte sidebar-inset.svelte sidebar-menu-action.svelte sidebar-menu-badge.svelte sidebar-menu-button.svelte sidebar-menu-item.svelte sidebar-menu-skeleton.svelte sidebar-menu-sub-button.svelte sidebar-menu-sub-item.svelte sidebar-menu-sub.svelte sidebar-menu.svelte sidebar-provider.svelte sidebar-rail.svelte sidebar-separator.svelte sidebar-trigger.svelte sidebar.svelte

skeleton

index.ts skeleton.svelte

switch

index.ts switch.svelte

table

index.ts table-body.svelte table-caption.svelte table-cell.svelte table-footer.svelte table-head.svelte table-header.svelte table-row.svelte table.svelte

textarea

index.ts textarea.svelte

tooltip

index.ts tooltip-content.svelte tooltip-trigger.svelte

utils.ts

auto-scroll.ts binary-detection.ts default-context.ts floating-ui-constraints.ts icons.ts input-classes.ts latex-protection.ts literal-html.ts localstorage-keys.ts max-bundle-size.ts precision.ts processing-info.ts settings-config.ts supported-file-types.ts table-html-restorer.ts tooltip-config.ts viewport.ts

enums

attachment.ts chat.ts files.ts index.ts model.ts server.ts

hooks

is-mobile.svelte.ts use-model-change-validation.svelte.ts use-processing-state.svelte.ts

markdown

enhance-code-blocks.ts enhance-links.ts literal-html.ts table-html-restorer.ts

services

chat.ts database.ts index.ts models.ts parameter-sync.spec.ts parameter-sync.ts props.ts

stores

chat.svelte.ts conversations.svelte.ts models.svelte.ts persisted.svelte.ts server.svelte.ts settings.svelte.ts

types

api.d.ts chat.d.ts database.d.ts index.ts models.d.ts settings.d.ts

utils

api-headers.ts api-key-validation.ts attachment-display.ts attachment-type.ts audio-recording.ts autoresize-textarea.ts branching.ts browser-only.ts clipboard.ts config-helpers.ts conversation-utils.ts convert-files-to-extra.ts file-preview.ts file-type.ts formatters.ts index.ts is-ime-composing.ts latex-protection.ts modality-file-validation.ts model-names.ts pdf-processing.ts portal-to-body.ts precision.ts process-uploaded-files.ts svg-to-png.ts syntax-highlight-language.ts text-files.ts text.ts webp-to-png.ts

routes

chat

[id]

+page.svelte +page.ts

+error.svelte +layout.svelte +page.svelte +page.ts

styles

katex-custom.scss

app.css app.d.ts app.html

static

favicon.svg loading.html

tests

client

TestWrapper.svelte

page.svelte.test.ts

e2e

stories

fixtures

assets

1.jpg beautiful-flowers-lotus.webp example.pdf hf-logo.svg

ai-tutorial.ts api-docs.ts blog-post.ts data-analysis.ts empty.ts math-formulas.ts readme.ts storybook-mocks.ts

ChatForm.stories.svelte ChatMessage.stories.svelte ChatSettings.stories.svelte ChatSidebar.stories.svelte Introduction.mdx MarkdownContent.stories.svelte

unit

clipboard.test.ts latex-protection.test.ts model-names.test.ts

.gitignore .npmrc .prettierignore .prettierrc README.md components.json eslint.config.js package-lock.json package.json playwright.config.ts svelte.config.js tsconfig.json vite.config.ts vitest-setup-client.ts

CMakeLists.txt README-dev.md README.md chat-llama2.sh chat.mjs chat.sh server-common.cpp server-common.h server-context.cpp server-context.h server-http.cpp server-http.h server-models.cpp server-models.h server-queue.cpp server-queue.h server-task.cpp server-task.h server.cpp

tokenize

CMakeLists.txt tokenize.cpp

tts

CMakeLists.txt README.md convert_pt_to_hf.py tts-outetts.py tts.cpp

vendor

CMakeLists.txt LICENSE httplib.cpp httplib.h

miniaudio.h

nlohmann

json.hpp json_fwd.hpp

sheredom

stb

stb_image.h

.clang-format .clang-tidy .dockerignore .ecrc .editorconfig .flake8 .gitignore .gitmodules .pre-commit-config.yaml AGENTS.md AUTHORS CLAUDE.md CMakeLists.txt CMakePresets.json CODEOWNERS CONTRIBUTING.md LICENSE Makefile README.md SECURITY.md convert_hf_to_gguf.py convert_hf_to_gguf_update.py convert_llama_ggml_to_gguf.py convert_lora_to_gguf.py flake.lock flake.nix mypy.ini poetry.lock pyproject.toml pyrightconfig.json requirements.txt

maps

map1.h map1.txt

papers

2310.11703v2.pdf 2405.14159v2.pdf

prompts

lotr.h lotr.txt

.gitignore Dockerfile Makefile README.md compile_flags.txt context.c game.c makext.mk mapeditor.html maps.h minunit.h models.h models.txt nonstd.h npc.c termbox2.h vectordb.c vectordb.h

llama.cpp/Makefile raw

1define newline
2
3
4endef
5
6$(error Build system changed:$(newline)\
7The Makefile build has been replaced by CMake.$(newline)$(newline)\
8For build instructions see:$(newline)\
9https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md$(newline)${newline})