mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-08-30 00:50:49 +02:00
Max Krasnyansky
192067b72d
* hexagon: use non-host bufs by default and make the backend fully async * hex-hb: remove optional hostbuf support and fix async copy * hex-unary: relax supported unary check * hex-bufs: use same get_alignment for host bufs * snapdragon: bump android_platform to 34 * hex-rows: super hacky get/set rows for q8_0 * hex-get-rows: fix q8_0 * hex-get-rows: supprot for f16 and cleanup for q8_0 * hex-get-rows: generic macros and specialized thread funcs * hex-get-rows: add DMA pipeline, vtcm_layout and kernel params * hex-set-rows: fix q8_0 support, add dma and tracing * hex-tests: override nmse threshold for HTP of Q8_0 quants * hex-fa: add support for Q8_0 with inplace dequantizers * hex-get-rows: simplify type dispatch * hex-rows: simplify GET/SET_ROWS DMA pipeline * hex-async: add events, set/get-tensor-async and rest of the async api support * hex-repack: use slice instead of expert in repack functions * hex-cpy: update event/async-cpy logging * hex-set-rows: optimize smaller tensors * hex-geglu: fix perf regression with larger tensors * hex-get-rows: add missing header * hex-set-rows: add missing header * hex-bufs: ressurect GGML_HEXAGON_HOSTBUF but disable it by default * hexagon: do not reject ops with non-heaxon buffers * hex-get-rows: apply >=32 restriction only for q8_0 * hex-res: bump vtcm acquire timeout to 10 seconds * hex-bufs: add support for cloning buffers between sessions to speed up tensor copies * hex-async: rework event recording and batch flushing and integrate with meta backend * hex-bufs: improved handling of repacked tensors * hex-repack: handle get_tensor_2d offsets * hex-dev: add support for devices with multiple NPUs * hex-sync: add support for sync tokens to synchronize npu devices for async splits * hex-mmap: cleanup mmap calls and add a retry for robustness * hex-sync: add failsafe if sync wait gets stuck * hex-sync: use sync_seq to check for completed events * hex-sync: rotate tokens for extra robustness * hex-devs: add supprot for legacy device names for now * hex-bufs: add support for auto-cloning buffers from diff sessions * hex-fusion: simplify and optimize htp-opnode fusion handling * hex-sync: override opnode name so that it shows up in the profiles * hex-trace: update scripts to handle multiple devices * hex-sync: bump the size of the opbatch queue and number of sync tokens * hex-cpy-sync: do not explicitly flush opbatches in cpy_tensor_async and add support for cpy-dma * hex-sync: add graph-flush threshold to avoid single op batches * hex-sync: add sync_peer so that we can flush peers we depend on during cross-device ops * hex-bufs: introduce tensor->extra and shadow_bufs for repacking * hex-l2: flush tiny tensors inline * hex-sync: use explicit l2flush for sync tokens * hex-extra: track weight flags via tensor extra * hex-fence: rename sync to fence * hex-repack: proper handling of set-tensor-2d in the shadow_buf * hex-trace: remove obsolete opstage mask that we used for profiling * hex-env: remove obsolete use_hmx variable * hexagon: new unified run.py and build.py and updated docs * snapdragon: update run script to auto-escapt test-backend-op -p argument * hex-scripts: fix trailing spaces * hex-scripts: fix flake8 warnings * snapdragon: cleanup dst lib/bin dirs before copying new build * hex-ops: add support for allreduce * hex-ar: improved allreduce with dma pipeline * hex-ar: align macros * hex-ar: consistent use of fence_seq * hex-ar: add AR_SELECT env var to select ALLREDUCE kernel or fallback * hex-ar: add proper synchronize handling for ALLREDUCE * hex-opbatch: looks like we now just rely on backend.synchronise to flush the batches, no need to flush them by threshold * hex-ar: bump block size to improve dma efficiency * hex-ar: fused ALLREDUCE+ADD * hex-ar: cleaner fence buffer management * hex-ar: futher allreduce tweaking to remove race conditions * hex-ar: add simple solver and remove non-dma kernels * hex-ar: add row-broadcast to fuse with bias ADD * hex-fence: pass seq numbers via op_params * hex-ar: allow for both entry/exit seq for completing entry wait * hex-ar: align macros * hex-ar: do not refetch broadcast row * hex-fusion: move all fusion into opbatch::add_op for consistency with ALLREDUCE and things * hex-fusion: fix incorrect MUL_MAT reordering * hex-mm: make fused 2x and 3x matmuls more generic * hex-fusion: move tensor fusion tagging to graph_compute * hexagon: make sure to copy tensor->extra by value * hex-get-rows: fix offset calc with row-chunking * hex-repack: get_tensor_2d fixes for non-zero offsets * snapdragon: make profile/trace scripts more robust and donot mix stdout/stderr by default * hex-devices: use legacy device nameing by default to ease the transition * hex-devices: hardcode CDSP domain IDs for current devices for now * hex-optrace: improve multi-NPU timestamp alignment and overall handling of cycle values * hex-optrace: more robust handling of the fence events
88 lines
4.3 KiB
JSON
88 lines
4.3 KiB
JSON
{
|
|
"version": 5,
|
|
"configurePresets": [
|
|
{
|
|
"name": "arm64-android-snapdragon",
|
|
"hidden": true,
|
|
"architecture": { "value": "arm64", "strategy": "external" },
|
|
"toolset": { "value": "host=x86_64", "strategy": "external" },
|
|
"cacheVariables": {
|
|
"ANDROID_ABI": "arm64-v8a",
|
|
"ANDROID_PLATFORM": "android-34",
|
|
"CMAKE_TOOLCHAIN_FILE": "$env{ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake",
|
|
"CMAKE_C_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -fno-finite-math-only -flto -D_GNU_SOURCE",
|
|
"CMAKE_CXX_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -fno-finite-math-only -flto -D_GNU_SOURCE",
|
|
"CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG",
|
|
"CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG",
|
|
"CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
|
|
"CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
|
|
"CMAKE_PREFIX_PATH": "$env{OPENCL_SDK_ROOT}",
|
|
"HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}",
|
|
"HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}",
|
|
"PREBUILT_LIB_DIR": "android_aarch64",
|
|
"GGML_OPENMP": "OFF",
|
|
"GGML_LLAMAFILE": "OFF",
|
|
"GGML_OPENCL": "ON",
|
|
"GGML_HEXAGON": "ON",
|
|
"LLAMA_OPENSSL": "OFF"
|
|
}
|
|
},
|
|
|
|
{
|
|
"name": "arm64-windows-snapdragon",
|
|
"inherits": [ "base", "arm64-windows-llvm" ],
|
|
"cacheVariables": {
|
|
"CMAKE_C_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -flto -D_GNU_SOURCE",
|
|
"CMAKE_CXX_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -flto -D_GNU_SOURCE",
|
|
"CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG",
|
|
"CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG",
|
|
"CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
|
|
"CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
|
|
"CMAKE_PREFIX_PATH": "$env{OPENCL_SDK_ROOT}",
|
|
"HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}",
|
|
"HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}",
|
|
"PREBUILT_LIB_DIR": "windows_aarch64",
|
|
"GGML_OPENMP": "OFF",
|
|
"GGML_LLAMAFILE": "OFF",
|
|
"GGML_OPENCL": "ON",
|
|
"GGML_HEXAGON": "ON",
|
|
"LLAMA_OPENSSL": "OFF"
|
|
}
|
|
},
|
|
|
|
{
|
|
"name": "arm64-linux-snapdragon",
|
|
"hidden": true,
|
|
"architecture": { "value": "arm64", "strategy": "external" },
|
|
"toolset": { "value": "host=x86_64", "strategy": "external" },
|
|
"cacheVariables": {
|
|
"CMAKE_TOOLCHAIN_FILE": "cmake/arm64-linux-clang.cmake",
|
|
"CMAKE_C_FLAGS": "-march=armv8.2a+fp16+dotprod -fvectorize -fno-finite-math-only -flto -D_GNU_SOURCE",
|
|
"CMAKE_CXX_FLAGS": "-march=armv8.2a+fp16+dotprod -fvectorize -fno-finite-math-only -flto -D_GNU_SOURCE",
|
|
"CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG",
|
|
"CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG",
|
|
"CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
|
|
"CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
|
|
"CMAKE_PREFIX_PATH": "$env{OPENCL_SDK_ROOT}",
|
|
"HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}",
|
|
"HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}",
|
|
"PREBUILT_LIB_DIR": "linux_aarch64",
|
|
"GGML_OPENMP": "OFF",
|
|
"GGML_LLAMAFILE": "OFF",
|
|
"GGML_OPENCL": "OFF",
|
|
"GGML_HEXAGON": "ON",
|
|
"LLAMA_OPENSSL": "OFF"
|
|
}
|
|
},
|
|
|
|
{ "name": "arm64-android-snapdragon-debug" , "inherits": [ "base", "arm64-android-snapdragon", "debug" ] },
|
|
{ "name": "arm64-android-snapdragon-release", "inherits": [ "base", "arm64-android-snapdragon", "release" ] },
|
|
|
|
{ "name": "arm64-windows-snapdragon-debug" , "inherits": [ "base", "arm64-windows-snapdragon", "debug" ] },
|
|
{ "name": "arm64-windows-snapdragon-release", "inherits": [ "base", "arm64-windows-snapdragon", "release" ] },
|
|
|
|
{ "name": "arm64-linux-snapdragon-debug" , "inherits": [ "base", "arm64-linux-snapdragon", "debug" ] },
|
|
{ "name": "arm64-linux-snapdragon-release", "inherits": [ "base", "arm64-linux-snapdragon", "release" ] }
|
|
]
|
|
}
|