cross-platform-llm-client
A unified cross-platform AI client supporting seamless transitions between standard cloud APIs and on-device, offline execution of custom and uncensored language models.
파일 탐색기
최종 버전 다운로드 (.zip)- launch.json
- settings.json
- AndroidManifest.xml
- libomp.so
- BootReceiver.kt
- MainActivity.kt
- launch_background.xml
- launch_background.xml
- ic_launcher.png
- ic_launcher.png
- ic_launcher.png
- ic_launcher.png
- ic_launcher.png
- styles.xml
- styles.xml
- AndroidManifest.xml
- AndroidManifest.xml
- build.gradle.kts
- problems-report.html
- gradle-wrapper.properties
- .gitignore
- build.gradle.kts
- gradle.properties
- key.properties.example
- settings.gradle.kts
- appicon.png
- webgpu_engine.html
- AppFrameworkInfo.plist
- Debug.xcconfig
- Release.xcconfig
- Contents.json
- Icon-App-1024x1024@1x.png
- Icon-App-20x20@1x.png
- Icon-App-20x20@2x.png
- Icon-App-20x20@3x.png
- Icon-App-29x29@1x.png
- Icon-App-29x29@2x.png
- Icon-App-29x29@3x.png
- Icon-App-40x40@1x.png
- Icon-App-40x40@2x.png
- Icon-App-40x40@3x.png
- Icon-App-60x60@2x.png
- Icon-App-60x60@3x.png
- Icon-App-76x76@1x.png
- Icon-App-76x76@2x.png
- Icon-App-83.5x83.5@2x.png
- Contents.json
- LaunchImage.png
- LaunchImage@2x.png
- LaunchImage@3x.png
- README.md
- LaunchScreen.storyboard
- Main.storyboard
- AppDelegate.swift
- Info.plist
- LlamaFlutterAndroidPlugin.h
- LlamaFlutterAndroidPlugin.m
- Runner-Bridging-Header.h
- IDEWorkspaceChecks.plist
- WorkspaceSettings.xcsettings
- contents.xcworkspacedata
- Runner.xcscheme
- project.pbxproj
- IDEWorkspaceChecks.plist
- WorkspaceSettings.xcsettings
- contents.xcworkspacedata
- RunnerTests.swift
- .gitignore
- Podfile
- Podfile.lock
- chat_controller.dart
- cloud_model_controller.dart
- home_controller.dart
- model_controller.dart
- server_controller.dart
- settings_controller.dart
- task_controller.dart
- colors.dart
- constants.dart
- routes.dart
- theme.dart
- sd_ffi_bindings.dart
- ai_model.dart
- chat_message.dart
- chat_session.dart
- task_model.dart
- app_log_service.dart
- cloud_service.dart
- crash_reporting_service.dart
- device_info_native.dart
- device_info_service.dart
- device_info_web.dart
- document_extractor_service.dart
- download_native.dart
- download_service.dart
- download_web.dart
- execution_service.dart
- hive_service.dart
- image_generation_notification_service.dart
- inference_android.dart
- inference_service.dart
- inference_stub.dart
- local_image_service.dart
- openai_server_service.dart
- openai_server_service_io.dart
- openai_server_service_stub.dart
- sd_isolate_processor.dart
- thought_parser.dart
- chat_view.dart
- home_view.dart
- log_view.dart
- model_view.dart
- server_view.dart
- settings_view.dart
- task_view.dart
- attachment_preview.dart
- chat_bubble.dart
- image_viewer.dart
- thought_disclosure.dart
- typing_indicator.dart
- main.dart
- FlutterLitertLmPlugin.kt
- AndroidManifest.xml
- FlutterLitertLmPluginTest.kt
- build.gradle.kts
- consumer-rules.pro
- settings.gradle
- settings.gradle.kts
- FlutterLitertLmPlugin.swift
- LiteLmNativeBridge.h
- LiteLmNativeBridge.mm
- README.md
- PrivacyInfo.xcprivacy
- flutter_litert_lm.podspec
- backend.dart
- config.dart
- content.dart
- conversation.dart
- engine.dart
- message.dart
- sampler_config.dart
- tool.dart
- flutter_litert_lm.dart
- flutter_litert_lm_method_channel.dart
- flutter_litert_lm_platform_interface.dart
- build_ios_frameworks.sh
- flutter_litert_lm_method_channel_test.dart
- flutter_litert_lm_test.dart
- analysis_options.yaml
- CHANGELOG.md
- CONTRIBUTING.md
- LICENSE
- pubspec.yaml
- README.md
- arm64-apple-clang.cmake
- arm64-linux-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
- caps.cpp
- caps.h
- lexer.cpp
- lexer.h
- parser.cpp
- parser.h
- README.md
- runtime.cpp
- runtime.h
- string.cpp
- string.h
- utils.h
- value.cpp
- value.h
- arg.cpp
- arg.h
- base64.hpp
- build-info.cpp.in
- chat-auto-parser-generator.cpp
- chat-auto-parser-helpers.cpp
- chat-auto-parser-helpers.h
- chat-auto-parser.h
- chat-diff-analyzer.cpp
- chat-peg-parser.cpp
- chat-peg-parser.h
- chat.cpp
- chat.h
- CMakeLists.txt
- common.cpp
- common.h
- console.cpp
- console.h
- debug.cpp
- debug.h
- download.cpp
- download.h
- hf-cache.cpp
- hf-cache.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
- reasoning-budget.cpp
- reasoning-budget.h
- regex-partial.cpp
- regex-partial.h
- sampling.cpp
- sampling.h
- speculative.cpp
- speculative.h
- unicode.cpp
- unicode.h
- common.cmake
- FindNCCL.cmake
- ggml-config.cmake.in
- GitVars.cmake
- 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-openvino.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
- CMakeLists.txt
- ggml-blas.cpp
- acl_tensor.cpp
- acl_tensor.h
- aclnn_ops.cpp
- aclnn_ops.h
- CMakeLists.txt
- common.h
- ggml-cann.cpp
- amx.cpp
- amx.h
- common.h
- mmq.cpp
- mmq.h
- cpu-feats.cpp
- quants.c
- repack.cpp
- quants.c
- cpu-feats.cpp
- quants.c
- cpu-feats.cpp
- quants.c
- repack.cpp
- cpu-feats.cpp
- quants.c
- quants.c
- cpu-feats.cpp
- quants.c
- repack.cpp
- FindSIMD.cmake
- kernels.cpp
- kernels.h
- kleidiai.cpp
- kleidiai.h
- sgemm.cpp
- sgemm.h
- ime.cpp
- ime.h
- ime1_kernels.cpp
- ime_kernels.h
- arch-fallback.h
- binary-ops.cpp
- binary-ops.h
- CMakeLists.txt
- 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-gemm.h
- simd-mappings.h
- traits.cpp
- traits.h
- unary-ops.cpp
- unary-ops.h
- vec.cpp
- vec.h
- 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-dkq512-dv512.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-bf16-bf16.cu
- fattn-vec-instance-bf16-f16.cu
- fattn-vec-instance-bf16-q4_0.cu
- fattn-vec-instance-bf16-q4_1.cu
- fattn-vec-instance-bf16-q5_0.cu
- fattn-vec-instance-bf16-q5_1.cu
- fattn-vec-instance-bf16-q8_0.cu
- fattn-vec-instance-f16-bf16.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-bf16.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-bf16.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-bf16.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-bf16.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-bf16.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-nvfp4.cu
- mmq-instance-q1_0.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
- cuda.h
- hip.h
- musa.h
- 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
- CMakeLists.txt
- 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
- gated_delta_net.cu
- gated_delta_net.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
- act-ops.c
- argsort-ops.c
- binary-ops.c
- cmake-toolchain.cmake
- CMakeLists.txt
- cpy-ops.c
- cumsum-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
- hmx-matmul-ops.c
- hmx-ops.h
- hmx-profile.h
- hmx-queue.c
- hmx-queue.h
- hmx-utils.h
- htp-ctx.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
- repeat-ops.c
- rope-ops.c
- set-rows-ops.c
- softmax-ops.c
- ssm-conv.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
- CMakeLists.txt
- 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
- add.cl
- add_id.cl
- argsort.cl
- clamp.cl
- concat.cl
- conv2d.cl
- conv2d_f16_f32.cl
- cpy.cl
- cumsum.cl
- cvt.cl
- diag.cl
- diag_mask_inf.cl
- div.cl
- embed_kernel.py
- exp.cl
- expm1.cl
- fill.cl
- flash_attn_f16.cl
- flash_attn_f32.cl
- flash_attn_f32_f16.cl
- gelu.cl
- gemm_moe_mxfp4_f32.cl
- gemm_noshuffle_q4_1_f32.cl
- gemm_noshuffle_q4_k_f32.cl
- gemm_noshuffle_q5_k_f32.cl
- gemm_noshuffle_q6_k_f32.cl
- gemv_moe_mxfp4_f32.cl
- gemv_noshuffle.cl
- gemv_noshuffle_general.cl
- gemv_noshuffle_general_q8_0_f32.cl
- gemv_noshuffle_q4_1_f32.cl
- gemv_noshuffle_q4_k_f32.cl
- gemv_noshuffle_q5_k_f32.cl
- gemv_noshuffle_q6_k_f32.cl
- get_rows.cl
- glu.cl
- group_norm.cl
- im2col_f16.cl
- im2col_f32.cl
- l2_norm.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_q4_0_f32_l4_lm.cl
- mul_mm_q4_1_f32_l4_lm.cl
- mul_mm_q4_k_f32_l4_lm.cl
- mul_mm_q5_k_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_1_f32.cl
- mul_mv_q4_1_f32_flat.cl
- mul_mv_q4_k_f32.cl
- mul_mv_q4_k_f32_flat.cl
- mul_mv_q5_k_f32.cl
- mul_mv_q5_k_f32_flat.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
- neg.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
- cont.cpp
- cpy.cpp
- flash_attn_ext.cpp
- get_rows.cpp
- glu_geglu.cpp
- glu_swiglu.cpp
- mulmat.cpp
- permute.cpp
- reshape.cpp
- rms_norm.cpp
- rope.cpp
- scale.cpp
- set_rows.cpp
- softmax.cpp
- transpose.cpp
- unary_silu.cpp
- view.cpp
- eliminate_zp.cpp
- eliminate_zp.h
- fuse_to_sdpa.cpp
- fuse_to_sdpa.h
- mark_decompression_convert_constant_folding.h
- squeeze_matmul.cpp
- squeeze_matmul.h
- decoder.h
- frontend.cpp
- frontend.h
- input_model.cpp
- input_model.h
- node_context.h
- op_table.cpp
- op_table.h
- translate_session.cpp
- translate_session.h
- utils.cpp
- utils.h
- CMakeLists.txt
- ggml-decoder.cpp
- ggml-decoder.h
- ggml-openvino-extra.cpp
- ggml-openvino-extra.h
- ggml-openvino.cpp
- ggml-quants.cpp
- ggml-quants.h
- utils.cpp
- utils.h
- CMakeLists.txt
- ggml-rpc.cpp
- helper.hpp
- fattn-tile-instance-dkq112-dv112.cpp
- fattn-tile-instance-dkq128-dv128.cpp
- fattn-tile-instance-dkq256-dv256.cpp
- fattn-tile-instance-dkq40-dv40.cpp
- fattn-tile-instance-dkq512-dv512.cpp
- fattn-tile-instance-dkq576-dv512.cpp
- fattn-tile-instance-dkq64-dv64.cpp
- fattn-tile-instance-dkq72-dv72.cpp
- fattn-tile-instance-dkq80-dv80.cpp
- fattn-tile-instance-dkq96-dv96.cpp
- fattn-vec-instance-f16-f16.cpp
- fattn-vec-instance-f16-q4_0.cpp
- fattn-vec-instance-f16-q4_1.cpp
- fattn-vec-instance-f16-q5_0.cpp
- fattn-vec-instance-f16-q5_1.cpp
- fattn-vec-instance-f16-q8_0.cpp
- fattn-vec-instance-q4_0-f16.cpp
- fattn-vec-instance-q4_0-q4_0.cpp
- fattn-vec-instance-q4_0-q4_1.cpp
- fattn-vec-instance-q4_0-q5_0.cpp
- fattn-vec-instance-q4_0-q5_1.cpp
- fattn-vec-instance-q4_0-q8_0.cpp
- fattn-vec-instance-q4_1-f16.cpp
- fattn-vec-instance-q4_1-q4_0.cpp
- fattn-vec-instance-q4_1-q4_1.cpp
- fattn-vec-instance-q4_1-q5_0.cpp
- fattn-vec-instance-q4_1-q5_1.cpp
- fattn-vec-instance-q4_1-q8_0.cpp
- fattn-vec-instance-q5_0-f16.cpp
- fattn-vec-instance-q5_0-q4_0.cpp
- fattn-vec-instance-q5_0-q4_1.cpp
- fattn-vec-instance-q5_0-q5_0.cpp
- fattn-vec-instance-q5_0-q5_1.cpp
- fattn-vec-instance-q5_0-q8_0.cpp
- fattn-vec-instance-q5_1-f16.cpp
- fattn-vec-instance-q5_1-q4_0.cpp
- fattn-vec-instance-q5_1-q4_1.cpp
- fattn-vec-instance-q5_1-q5_0.cpp
- fattn-vec-instance-q5_1-q5_1.cpp
- fattn-vec-instance-q5_1-q8_0.cpp
- fattn-vec-instance-q8_0-f16.cpp
- fattn-vec-instance-q8_0-q4_0.cpp
- fattn-vec-instance-q8_0-q4_1.cpp
- fattn-vec-instance-q8_0-q5_0.cpp
- fattn-vec-instance-q8_0-q5_1.cpp
- fattn-vec-instance-q8_0-q8_0.cpp
- add-id.cpp
- add-id.hpp
- backend.hpp
- binbcast.cpp
- binbcast.hpp
- CMakeLists.txt
- 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
- fattn-common.hpp
- fattn-tile.cpp
- fattn-tile.hpp
- fattn-vec.hpp
- fattn.cpp
- fattn.hpp
- gated_delta_net.cpp
- gated_delta_net.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
- type.hpp
- upscale.cpp
- upscale.hpp
- vecdotq.hpp
- wkv.cpp
- wkv.hpp
- api_remoting.h
- apir_backend.gen.h
- apir_backend.h
- apir_cs.h
- apir_cs_ggml.h
- apir_cs_rpc.h
- 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
- CMakeLists.txt
- apir_hw.h
- apir_cs_ggml-rpc-front.cpp
- CMakeLists.txt
- 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
- host-toolchain.cmake.in
- bfloat16.comp
- coopmat.comp
- coopmat2.comp
- integer_dot.comp
- abs.comp
- acc.comp
- add.comp
- add1.comp
- add_id.comp
- arange.comp
- argmax.comp
- argsort.comp
- argsort_large.comp
- ceil.comp
- clamp.comp
- CMakeLists.txt
- 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_nvfp4.comp
- dequant_q1_0.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
- elu.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_mmq_funcs.glsl
- flash_attn_split_k_reduce.comp
- floor.comp
- gated_delta_net.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
- scale.comp
- sgn.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
- concat.wgsl
- cpy.wgsl
- cumsum.wgsl
- embed_wgsl.py
- flash_attn.wgsl
- flash_attn_vec_blk.wgsl
- flash_attn_vec_reduce.wgsl
- flash_attn_vec_split.wgsl
- gated_delta_net.wgsl
- get_rows.wgsl
- glu.wgsl
- memset.wgsl
- mul_mat.wgsl
- mul_mat_decls.tmpl
- mul_mat_id.wgsl
- mul_mat_id_gather.wgsl
- mul_mat_reg_tile.wgsl
- mul_mat_subgroup_matrix.wgsl
- mul_mat_vec.wgsl
- pad.wgsl
- repeat.wgsl
- rope.wgsl
- row_norm.wgsl
- scale.wgsl
- set.wgsl
- set_rows.wgsl
- soft_max.wgsl
- solve_tri.wgsl
- ssm_conv.wgsl
- sum_rows.wgsl
- unary.wgsl
- CMakeLists.txt
- ggml-webgpu-shader-lib.hpp
- ggml-webgpu.cpp
- pre_wgsl.hpp
- 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-meta.cpp
- 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
- CMakeLists.txt
- llama-cpp.h
- llama.h
- 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
- delta-net-base.cpp
- dots1.cpp
- dream.cpp
- ernie4-5-moe.cpp
- ernie4-5.cpp
- eurobert.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
- gemma4-iswa.cpp
- glm4-moe.cpp
- glm4.cpp
- gpt2.cpp
- gptneox.cpp
- granite-hybrid.cpp
- granite.cpp
- grok.cpp
- grovemoe.cpp
- hunyuan-dense.cpp
- hunyuan-moe.cpp
- internlm2.cpp
- jais.cpp
- jais2.cpp
- jamba.cpp
- kimi-linear.cpp
- lfm2.cpp
- llada-moe.cpp
- llada.cpp
- llama.cpp
- llama4.cpp
- maincoder.cpp
- mamba-base.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
- paddleocr.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.cpp
- t5encoder.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-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
- CMakeLists.txt
- CMakePresets.json
- LICENSE
- jni_wrapper.cpp
- ChatTemplates.kt
- InferenceService.kt
- LlamaFlutterAndroidPlugin.kt
- LlamaHostApi.kt
- AndroidManifest.xml
- LlamaFlutterAndroidPluginTest.kt
- ChatTemplateTest.kt
- build.gradle.kts
- CMakeLists.txt
- settings.gradle
- ChatTemplates.swift
- GeneratedMessages.g.swift
- LlamaFlutterAndroidPlugin.swift
- LlamaIosWrapper.h
- LlamaIosWrapper.mm
- ObjcExceptionBridge.h
- ObjcExceptionBridge.swift
- common.cmake
- FindNCCL.cmake
- ggml-config.cmake.in
- GitVars.cmake
- 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-openvino.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
- CMakeLists.txt
- ggml-blas.cpp
- acl_tensor.cpp
- acl_tensor.h
- aclnn_ops.cpp
- aclnn_ops.h
- CMakeLists.txt
- common.h
- ggml-cann.cpp
- amx.cpp
- amx.h
- common.h
- mmq.cpp
- mmq.h
- cpu-feats.cpp
- quants.c
- repack.cpp
- quants.c
- cpu-feats.cpp
- quants.c
- cpu-feats.cpp
- quants.c
- repack.cpp
- cpu-feats.cpp
- quants.c
- quants.c
- cpu-feats.cpp
- quants.c
- repack.cpp
- FindSIMD.cmake
- kernels.cpp
- kernels.h
- kleidiai.cpp
- kleidiai.h
- sgemm.cpp
- sgemm.h
- ime.cpp
- ime.h
- ime1_kernels.cpp
- ime_kernels.h
- arch-fallback.h
- binary-ops.cpp
- binary-ops.h
- CMakeLists.txt
- 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-gemm.h
- simd-mappings.h
- traits.cpp
- traits.h
- unary-ops.cpp
- unary-ops.h
- vec.cpp
- vec.h
- 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-dkq512-dv512.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-bf16-bf16.cu
- fattn-vec-instance-bf16-f16.cu
- fattn-vec-instance-bf16-q4_0.cu
- fattn-vec-instance-bf16-q4_1.cu
- fattn-vec-instance-bf16-q5_0.cu
- fattn-vec-instance-bf16-q5_1.cu
- fattn-vec-instance-bf16-q8_0.cu
- fattn-vec-instance-f16-bf16.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-bf16.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-bf16.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-bf16.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-bf16.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-bf16.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-nvfp4.cu
- mmq-instance-q1_0.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
- cuda.h
- hip.h
- musa.h
- 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
- CMakeLists.txt
- 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
- gated_delta_net.cu
- gated_delta_net.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
- act-ops.c
- argsort-ops.c
- binary-ops.c
- cmake-toolchain.cmake
- CMakeLists.txt
- cpy-ops.c
- cumsum-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
- hmx-matmul-ops.c
- hmx-ops.h
- hmx-profile.h
- hmx-queue.c
- hmx-queue.h
- hmx-utils.h
- htp-ctx.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
- repeat-ops.c
- rope-ops.c
- set-rows-ops.c
- softmax-ops.c
- ssm-conv.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
- CMakeLists.txt
- 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-ios.metal
- ggml-metal-ops.cpp
- ggml-metal-ops.h
- ggml-metal.cpp
- ggml-metal.metal
- CMakeLists.txt
- mudnn.cu
- mudnn.cuh
- add.cl
- add_id.cl
- argsort.cl
- clamp.cl
- concat.cl
- conv2d.cl
- conv2d_f16_f32.cl
- cpy.cl
- cumsum.cl
- cvt.cl
- diag.cl
- diag_mask_inf.cl
- div.cl
- embed_kernel.py
- exp.cl
- expm1.cl
- fill.cl
- flash_attn_f16.cl
- flash_attn_f32.cl
- flash_attn_f32_f16.cl
- gelu.cl
- gemm_moe_mxfp4_f32.cl
- gemm_noshuffle_q4_1_f32.cl
- gemm_noshuffle_q4_k_f32.cl
- gemm_noshuffle_q5_k_f32.cl
- gemm_noshuffle_q6_k_f32.cl
- gemv_moe_mxfp4_f32.cl
- gemv_noshuffle.cl
- gemv_noshuffle_general.cl
- gemv_noshuffle_general_q8_0_f32.cl
- gemv_noshuffle_q4_1_f32.cl
- gemv_noshuffle_q4_k_f32.cl
- gemv_noshuffle_q5_k_f32.cl
- gemv_noshuffle_q6_k_f32.cl
- get_rows.cl
- glu.cl
- group_norm.cl
- im2col_f16.cl
- im2col_f32.cl
- l2_norm.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_q4_0_f32_l4_lm.cl
- mul_mm_q4_1_f32_l4_lm.cl
- mul_mm_q4_k_f32_l4_lm.cl
- mul_mm_q5_k_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_1_f32.cl
- mul_mv_q4_1_f32_flat.cl
- mul_mv_q4_k_f32.cl
- mul_mv_q4_k_f32_flat.cl
- mul_mv_q5_k_f32.cl
- mul_mv_q5_k_f32_flat.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
- neg.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
- cont.cpp
- cpy.cpp
- flash_attn_ext.cpp
- get_rows.cpp
- glu_geglu.cpp
- glu_swiglu.cpp
- mulmat.cpp
- permute.cpp
- reshape.cpp
- rms_norm.cpp
- rope.cpp
- scale.cpp
- set_rows.cpp
- softmax.cpp
- transpose.cpp
- unary_silu.cpp
- view.cpp
- eliminate_zp.cpp
- eliminate_zp.h
- fuse_to_sdpa.cpp
- fuse_to_sdpa.h
- mark_decompression_convert_constant_folding.h
- squeeze_matmul.cpp
- squeeze_matmul.h
- decoder.h
- frontend.cpp
- frontend.h
- input_model.cpp
- input_model.h
- node_context.h
- op_table.cpp
- op_table.h
- translate_session.cpp
- translate_session.h
- utils.cpp
- utils.h
- CMakeLists.txt
- ggml-decoder.cpp
- ggml-decoder.h
- ggml-openvino-extra.cpp
- ggml-openvino-extra.h
- ggml-openvino.cpp
- ggml-quants.cpp
- ggml-quants.h
- utils.cpp
- utils.h
- CMakeLists.txt
- ggml-rpc.cpp
- helper.hpp
- fattn-tile-instance-dkq112-dv112.cpp
- fattn-tile-instance-dkq128-dv128.cpp
- fattn-tile-instance-dkq256-dv256.cpp
- fattn-tile-instance-dkq40-dv40.cpp
- fattn-tile-instance-dkq512-dv512.cpp
- fattn-tile-instance-dkq576-dv512.cpp
- fattn-tile-instance-dkq64-dv64.cpp
- fattn-tile-instance-dkq72-dv72.cpp
- fattn-tile-instance-dkq80-dv80.cpp
- fattn-tile-instance-dkq96-dv96.cpp
- fattn-vec-instance-f16-f16.cpp
- fattn-vec-instance-f16-q4_0.cpp
- fattn-vec-instance-f16-q4_1.cpp
- fattn-vec-instance-f16-q5_0.cpp
- fattn-vec-instance-f16-q5_1.cpp
- fattn-vec-instance-f16-q8_0.cpp
- fattn-vec-instance-q4_0-f16.cpp
- fattn-vec-instance-q4_0-q4_0.cpp
- fattn-vec-instance-q4_0-q4_1.cpp
- fattn-vec-instance-q4_0-q5_0.cpp
- fattn-vec-instance-q4_0-q5_1.cpp
- fattn-vec-instance-q4_0-q8_0.cpp
- fattn-vec-instance-q4_1-f16.cpp
- fattn-vec-instance-q4_1-q4_0.cpp
- fattn-vec-instance-q4_1-q4_1.cpp
- fattn-vec-instance-q4_1-q5_0.cpp
- fattn-vec-instance-q4_1-q5_1.cpp
- fattn-vec-instance-q4_1-q8_0.cpp
- fattn-vec-instance-q5_0-f16.cpp
- fattn-vec-instance-q5_0-q4_0.cpp
- fattn-vec-instance-q5_0-q4_1.cpp
- fattn-vec-instance-q5_0-q5_0.cpp
- fattn-vec-instance-q5_0-q5_1.cpp
- fattn-vec-instance-q5_0-q8_0.cpp
- fattn-vec-instance-q5_1-f16.cpp
- fattn-vec-instance-q5_1-q4_0.cpp
- fattn-vec-instance-q5_1-q4_1.cpp
- fattn-vec-instance-q5_1-q5_0.cpp
- fattn-vec-instance-q5_1-q5_1.cpp
- fattn-vec-instance-q5_1-q8_0.cpp
- fattn-vec-instance-q8_0-f16.cpp
- fattn-vec-instance-q8_0-q4_0.cpp
- fattn-vec-instance-q8_0-q4_1.cpp
- fattn-vec-instance-q8_0-q5_0.cpp
- fattn-vec-instance-q8_0-q5_1.cpp
- fattn-vec-instance-q8_0-q8_0.cpp
- add-id.cpp
- add-id.hpp
- backend.hpp
- binbcast.cpp
- binbcast.hpp
- CMakeLists.txt
- 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
- fattn-common.hpp
- fattn-tile.cpp
- fattn-tile.hpp
- fattn-vec.hpp
- fattn.cpp
- fattn.hpp
- gated_delta_net.cpp
- gated_delta_net.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
- type.hpp
- upscale.cpp
- upscale.hpp
- vecdotq.hpp
- wkv.cpp
- wkv.hpp
- api_remoting.h
- apir_backend.gen.h
- apir_backend.h
- apir_cs.h
- apir_cs_ggml.h
- apir_cs_rpc.h
- 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
- CMakeLists.txt
- apir_hw.h
- apir_cs_ggml-rpc-front.cpp
- CMakeLists.txt
- 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
- host-toolchain.cmake.in
- bfloat16.comp
- coopmat.comp
- coopmat2.comp
- integer_dot.comp
- abs.comp
- acc.comp
- add.comp
- add1.comp
- add_id.comp
- arange.comp
- argmax.comp
- argsort.comp
- argsort_large.comp
- ceil.comp
- clamp.comp
- CMakeLists.txt
- 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_nvfp4.comp
- dequant_q1_0.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
- elu.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_mmq_funcs.glsl
- flash_attn_split_k_reduce.comp
- floor.comp
- gated_delta_net.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
- scale.comp
- sgn.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
- concat.wgsl
- cpy.wgsl
- cumsum.wgsl
- embed_wgsl.py
- flash_attn.wgsl
- flash_attn_vec_blk.wgsl
- flash_attn_vec_reduce.wgsl
- flash_attn_vec_split.wgsl
- gated_delta_net.wgsl
- get_rows.wgsl
- glu.wgsl
- memset.wgsl
- mul_mat.wgsl
- mul_mat_decls.tmpl
- mul_mat_id.wgsl
- mul_mat_id_gather.wgsl
- mul_mat_reg_tile.wgsl
- mul_mat_subgroup_matrix.wgsl
- mul_mat_vec.wgsl
- pad.wgsl
- repeat.wgsl
- rope.wgsl
- row_norm.wgsl
- scale.wgsl
- set.wgsl
- set_rows.wgsl
- soft_max.wgsl
- solve_tri.wgsl
- ssm_conv.wgsl
- sum_rows.wgsl
- unary.wgsl
- CMakeLists.txt
- ggml-webgpu-shader-lib.hpp
- ggml-webgpu.cpp
- pre_wgsl.hpp
- 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-meta.cpp
- 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
- CMakeLists.txt
- llama-cpp.h
- llama.h
- 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
- delta-net-base.cpp
- dots1.cpp
- dream.cpp
- ernie4-5-moe.cpp
- ernie4-5.cpp
- eurobert.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
- gemma4-iswa.cpp
- glm4-moe.cpp
- glm4.cpp
- gpt2.cpp
- gptneox.cpp
- granite-hybrid.cpp
- granite.cpp
- grok.cpp
- grovemoe.cpp
- hunyuan-dense.cpp
- hunyuan-moe.cpp
- internlm2.cpp
- jais.cpp
- jais2.cpp
- jamba.cpp
- kimi-linear.cpp
- lfm2.cpp
- llada-moe.cpp
- llada.cpp
- llama.cpp
- llama4.cpp
- maincoder.cpp
- mamba-base.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
- paddleocr.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.cpp
- t5encoder.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-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
- llama_flutter_android.podspec
- context_strategy.dart
- generation_config.dart
- llama_api.dart
- llama_controller.dart
- llama_flutter_android.dart
- llama_flutter_android_method_channel.dart
- llama_flutter_android_platform_interface.dart
- analysis_options.yaml
- CHANGELOG.md
- CONTRIBUTING.md
- LICENSE
- pubspec.yaml
- README.md
- FindOpenCL.cmake
- FindVulkan.cmake
- cl.h
- cl_d3d10.h
- cl_d3d11.h
- cl_dx9_media_sharing.h
- cl_dx9_media_sharing_intel.h
- cl_egl.h
- cl_ext.h
- cl_ext_intel.h
- cl_function_types.h
- cl_gl.h
- cl_gl_ext.h
- cl_half.h
- cl_icd.h
- cl_layer.h
- cl_platform.h
- cl_va_api_media_sharing_intel.h
- cl_version.h
- opencl.h
- sd_jni_wrapper.cpp
- stable-diffusion.cpp
- libomp.so
- libsd_jni.so
- libsd_jni_opencl.so
- libsd_jni_vulkan.so
- SdFlutterAndroidPlugin.kt
- AndroidManifest.xml
- SdFlutterAndroidPluginTest.kt
- .gitignore
- build.gradle
- CMakeLists.txt
- settings.gradle
- gradle-wrapper.jar
- gradlew
- gradlew.bat
- local.properties
- .gitkeep
- SdFlutterAndroidPlugin.swift
- SdIosWrapper.h
- SdIosWrapper.mm
- PrivacyInfo.xcprivacy
- .gitignore
- sd_flutter_android.podspec
- sd_flutter_android.dart
- sd_flutter_android_method_channel.dart
- sd_flutter_android_platform_interface.dart
- build_gpu_backends_wsl.sh
- fix_ndk_symlinks.py
- sd_flutter_android_method_channel_test.dart
- sd_flutter_android_test.dart
- .gitignore
- .metadata
- analysis_options.yaml
- CHANGELOG.md
- LICENSE
- pubspec.yaml
- README.md
- .gitignore
- ai_model_test.dart
- Icon-192.png
- Icon-512.png
- Icon-maskable-192.png
- Icon-maskable-512.png
- favicon.png
- index.html
- manifest.json
- .firebaserc
- .gitignore
- .gitmodules
- .metadata
- analysis_options.yaml
- firebase.json
- IMG_2390.png
- LICENSE
- PrivateLM.png
- pubspec.lock
- pubspec.yaml
- README.md
// repository documentation
Was this content helpful?
(0 ratings)