diff --git a/.github/workflows/check-vendor.yml b/.github/workflows/check-vendor.yml new file mode 100644 index 0000000000..7b3016079c --- /dev/null +++ b/.github/workflows/check-vendor.yml @@ -0,0 +1,52 @@ +name: Check vendor + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: [ + 'vendor/**', + 'scripts/sync_vendor.py' + ] + + pull_request: + types: [opened, synchronize, reopened] + paths: [ + 'vendor/**', + 'scripts/sync_vendor.py' + ] + +jobs: + check-vendor: + runs-on: ubuntu-latest + + steps: + - name: Checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Setup Python + uses: actions/setup-python@v4 + with: + python-version: '3.x' + + - name: Run vendor sync + run: | + set -euo pipefail + python3 scripts/sync_vendor.py + + - name: Check for changes + run: | + set -euo pipefail + # detect modified or untracked files + changed=$(git status --porcelain --untracked-files=all || true) + if [ -n "$changed" ]; then + echo "Vendor sync modified files:" + echo "$changed" | awk '{ print $2 }' | sed '/^$/d' + echo "Failing because vendor files mismatch. Please update scripts/sync_vendor.py" + exit 1 + else + echo "Vendor files are up-to-date." + fi diff --git a/.github/workflows/server.yml b/.github/workflows/server.yml index 1ea1300c2e..ebcd6424bc 100644 --- a/.github/workflows/server.yml +++ b/.github/workflows/server.yml @@ -209,7 +209,7 @@ jobs: working-directory: tools/server/webui - name: Run UI tests - run: npm run test:ui + run: npm run test:ui -- --testTimeout=60000 working-directory: tools/server/webui - name: Run E2E tests diff --git a/CMakeLists.txt b/CMakeLists.txt index e7410184df..3278c4a72c 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -92,6 +92,7 @@ option(LLAMA_TOOLS_INSTALL "llama: install tools" ${LLAMA_TOOLS_INSTALL_ # 3rd party libs option(LLAMA_CURL "llama: use libcurl to download model from an URL" ON) +option(LLAMA_HTTPLIB "llama: if libcurl is disabled, use httplib to download model from an URL" ON) option(LLAMA_OPENSSL "llama: use openssl to support HTTPS" OFF) option(LLAMA_LLGUIDANCE "llama-common: include LLGuidance library for structured output in common utils" OFF) @@ -200,7 +201,9 @@ endif() if (LLAMA_BUILD_COMMON) add_subdirectory(common) - add_subdirectory(vendor/cpp-httplib) + if (LLAMA_HTTPLIB) + add_subdirectory(vendor/cpp-httplib) + endif() endif() if (LLAMA_BUILD_COMMON AND LLAMA_BUILD_TESTS AND NOT CMAKE_JS_VERSION) diff --git a/build-xcframework.sh b/build-xcframework.sh index 796f8016ca..81280f7497 100755 --- a/build-xcframework.sh +++ b/build-xcframework.sh @@ -454,6 +454,8 @@ cmake -B build-visionos -G Xcode \ -DCMAKE_C_FLAGS="-D_XOPEN_SOURCE=700 ${COMMON_C_FLAGS}" \ -DCMAKE_CXX_FLAGS="-D_XOPEN_SOURCE=700 ${COMMON_CXX_FLAGS}" \ -DLLAMA_CURL=OFF \ + -DLLAMA_HTTPLIB=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ -S . cmake --build build-visionos --config Release -- -quiet @@ -468,6 +470,8 @@ cmake -B build-visionos-sim -G Xcode \ -DCMAKE_C_FLAGS="-D_XOPEN_SOURCE=700 ${COMMON_C_FLAGS}" \ -DCMAKE_CXX_FLAGS="-D_XOPEN_SOURCE=700 ${COMMON_CXX_FLAGS}" \ -DLLAMA_CURL=OFF \ + -DLLAMA_HTTPLIB=OFF \ + -DLLAMA_BUILD_SERVER=OFF \ -S . cmake --build build-visionos-sim --config Release -- -quiet diff --git a/common/CMakeLists.txt b/common/CMakeLists.txt index 1d260507ad..706fa32eed 100644 --- a/common/CMakeLists.txt +++ b/common/CMakeLists.txt @@ -91,47 +91,12 @@ if (LLAMA_CURL) target_compile_definitions(${TARGET} PUBLIC LLAMA_USE_CURL) include_directories(${CURL_INCLUDE_DIRS}) set(LLAMA_COMMON_EXTRA_LIBS ${LLAMA_COMMON_EXTRA_LIBS} ${CURL_LIBRARIES}) -else() +elseif (LLAMA_HTTPLIB) # otherwise, use cpp-httplib + target_compile_definitions(${TARGET} PUBLIC LLAMA_USE_HTTPLIB) set(LLAMA_COMMON_EXTRA_LIBS ${LLAMA_COMMON_EXTRA_LIBS} cpp-httplib) endif() -if (LLAMA_OPENSSL) - find_package(OpenSSL) - if (OpenSSL_FOUND) - include(CheckCSourceCompiles) - set(SAVED_CMAKE_REQUIRED_INCLUDES ${CMAKE_REQUIRED_INCLUDES}) - set(CMAKE_REQUIRED_INCLUDES ${OPENSSL_INCLUDE_DIR}) - check_c_source_compiles(" - #include - #if defined(OPENSSL_IS_BORINGSSL) || defined(LIBRESSL_VERSION_NUMBER) - # if OPENSSL_VERSION_NUMBER < 0x1010107f - # error bad version - # endif - #else - # if OPENSSL_VERSION_NUMBER < 0x30000000L - # error bad version - # endif - #endif - int main() { return 0; } - " OPENSSL_VERSION_SUPPORTED) - set(CMAKE_REQUIRED_INCLUDES ${SAVED_CMAKE_REQUIRED_INCLUDES}) - if (OPENSSL_VERSION_SUPPORTED) - message(STATUS "OpenSSL found: ${OPENSSL_VERSION}") - target_compile_definitions(${TARGET} PUBLIC CPPHTTPLIB_OPENSSL_SUPPORT) - target_link_libraries(${TARGET} PUBLIC OpenSSL::SSL OpenSSL::Crypto) - if (APPLE AND CMAKE_SYSTEM_NAME STREQUAL "Darwin") - target_compile_definitions(${TARGET} PUBLIC CPPHTTPLIB_USE_CERTS_FROM_MACOSX_KEYCHAIN) - find_library(CORE_FOUNDATION_FRAMEWORK CoreFoundation REQUIRED) - find_library(SECURITY_FRAMEWORK Security REQUIRED) - target_link_libraries(${TARGET} PUBLIC ${CORE_FOUNDATION_FRAMEWORK} ${SECURITY_FRAMEWORK}) - endif() - endif() - else() - message(STATUS "OpenSSL not found, SSL support disabled") - endif() -endif() - if (LLAMA_LLGUIDANCE) include(ExternalProject) set(LLGUIDANCE_SRC ${CMAKE_BINARY_DIR}/llguidance/source) diff --git a/common/download.cpp b/common/download.cpp index 57308a5c6d..eeb32b6a86 100644 --- a/common/download.cpp +++ b/common/download.cpp @@ -20,7 +20,7 @@ #if defined(LLAMA_USE_CURL) #include #include -#else +#elif defined(LLAMA_USE_HTTPLIB) #include "http.h" #endif @@ -467,7 +467,7 @@ std::pair> common_remote_get_content(const std::string & return { res_code, std::move(res_buffer) }; } -#else +#elif defined(LLAMA_USE_HTTPLIB) static bool is_output_a_tty() { #if defined(_WIN32) @@ -713,6 +713,8 @@ std::pair> common_remote_get_content(const std::string #endif // LLAMA_USE_CURL +#if defined(LLAMA_USE_CURL) || defined(LLAMA_USE_HTTPLIB) + static bool common_download_file_single(const std::string & url, const std::string & path, const std::string & bearer_token, @@ -907,33 +909,6 @@ common_hf_file_res common_get_hf_file(const std::string & hf_repo_with_tag, cons return { hf_repo, ggufFile, mmprojFile }; } -std::vector common_list_cached_models() { - std::vector models; - const std::string cache_dir = fs_get_cache_directory(); - const std::vector files = fs_list_files(cache_dir); - for (const auto & file : files) { - if (string_starts_with(file.name, "manifest=") && string_ends_with(file.name, ".json")) { - common_cached_model_info model_info; - model_info.manifest_path = file.path; - std::string fname = file.name; - string_replace_all(fname, ".json", ""); // remove extension - auto parts = string_split(fname, '='); - if (parts.size() == 4) { - // expect format: manifest==== - model_info.user = parts[1]; - model_info.model = parts[2]; - model_info.tag = parts[3]; - } else { - // invalid format - continue; - } - model_info.size = 0; // TODO: get GGUF size, not manifest size - models.push_back(model_info); - } - } - return models; -} - // // Docker registry functions // @@ -1052,3 +1027,46 @@ std::string common_docker_resolve_model(const std::string & docker) { throw; } } + +#else + +common_hf_file_res common_get_hf_file(const std::string &, const std::string &, bool) { + throw std::runtime_error("download functionality is not enabled in this build"); +} + +bool common_download_model(const common_params_model &, const std::string &, bool) { + throw std::runtime_error("download functionality is not enabled in this build"); +} + +std::string common_docker_resolve_model(const std::string &) { + throw std::runtime_error("download functionality is not enabled in this build"); +} + +#endif // LLAMA_USE_CURL || LLAMA_USE_HTTPLIB + +std::vector common_list_cached_models() { + std::vector models; + const std::string cache_dir = fs_get_cache_directory(); + const std::vector files = fs_list_files(cache_dir); + for (const auto & file : files) { + if (string_starts_with(file.name, "manifest=") && string_ends_with(file.name, ".json")) { + common_cached_model_info model_info; + model_info.manifest_path = file.path; + std::string fname = file.name; + string_replace_all(fname, ".json", ""); // remove extension + auto parts = string_split(fname, '='); + if (parts.size() == 4) { + // expect format: manifest==== + model_info.user = parts[1]; + model_info.model = parts[2]; + model_info.tag = parts[3]; + } else { + // invalid format + continue; + } + model_info.size = 0; // TODO: get GGUF size, not manifest size + models.push_back(model_info); + } + } + return models; +} diff --git a/docs/backend/CANN.md b/docs/backend/CANN.md index e45fc7dd28..37dcfaef9a 100755 --- a/docs/backend/CANN.md +++ b/docs/backend/CANN.md @@ -313,7 +313,12 @@ Converting the matmul weight format from ND to NZ to improve performance. Enable ### GGML_CANN_ACL_GRAPH -Operators are executed using ACL graph execution, rather than in op-by-op (eager) mode. Enabled by default. +Operators are executed using ACL graph execution, rather than in op-by-op (eager) mode. Enabled by default. This option is only effective if `USE_ACL_GRAPH` was enabled at compilation time. To enable it, recompile using: + +```sh +cmake -B build -DGGML_CANN=on -DCMAKE_BUILD_TYPE=release -DUSE_ACL_GRAPH=ON +cmake --build build --config release +``` ### GGML_CANN_GRAPH_CACHE_CAPACITY diff --git a/ggml/src/ggml-cann/aclnn_ops.cpp b/ggml/src/ggml-cann/aclnn_ops.cpp index 5df6dc96a3..4835c5c038 100644 --- a/ggml/src/ggml-cann/aclnn_ops.cpp +++ b/ggml/src/ggml-cann/aclnn_ops.cpp @@ -448,6 +448,35 @@ void ggml_cann_norm(ggml_backend_cann_context & ctx, ggml_tensor * dst) { ggml_cann_release_resources(ctx, norm, acl_src, acl_dst); } +void ggml_cann_l2_norm(ggml_backend_cann_context & ctx, ggml_tensor * dst) { + ggml_tensor * src = dst->src[0]; + + aclTensor * acl_src = ggml_cann_create_tensor(src); + aclTensor * acl_dst = ggml_cann_create_tensor(dst); + + size_t type_size = ggml_type_size(src->type); + int64_t n_bytes = src->ne[3]* src->ne[2]* src->ne[1]* type_size; + ggml_cann_pool_alloc temp_buffer_allocator(ctx.pool(), n_bytes); + void * buffer = temp_buffer_allocator.get(); + + int64_t div_ne[] = {1, src->ne[1], src->ne[2], src->ne[3]}; + size_t div_nb[GGML_MAX_DIMS]; + div_nb[0] = sizeof(float); + for (int i = 1; i < GGML_MAX_DIMS; ++i) { + div_nb[i] = div_nb[i - 1] * div_ne[i - 1]; + } + aclTensor * acl_div = ggml_cann_create_tensor(buffer, ACL_FLOAT, type_size, div_ne, div_nb, GGML_MAX_DIMS); + + std::vector norm_dims = { 3 }; + aclIntArray * dims_array = aclCreateIntArray(norm_dims.data(), norm_dims.size()); + + float p_value = 2.0f; + aclScalar * p_scalar = aclCreateScalar(&p_value, aclDataType::ACL_FLOAT); + GGML_CANN_CALL_ACLNN_OP(ctx, Norm, acl_src, p_scalar, dims_array, true, acl_div); + GGML_CANN_CALL_ACLNN_OP(ctx, Div, acl_src, acl_div, acl_dst); + ggml_cann_release_resources(ctx, dims_array, p_scalar, acl_src, acl_dst, acl_div); +} + void ggml_cann_group_norm(ggml_backend_cann_context & ctx, ggml_tensor * dst) { ggml_tensor * src = dst->src[0]; diff --git a/ggml/src/ggml-cann/aclnn_ops.h b/ggml/src/ggml-cann/aclnn_ops.h index ec7455af88..060eedbbb0 100644 --- a/ggml/src/ggml-cann/aclnn_ops.h +++ b/ggml/src/ggml-cann/aclnn_ops.h @@ -46,6 +46,7 @@ #include #include #include +#include #include "acl_tensor.h" #include "common.h" @@ -187,6 +188,29 @@ void ggml_cann_argsort(ggml_backend_cann_context & ctx, ggml_tensor * dst); */ void ggml_cann_norm(ggml_backend_cann_context & ctx, ggml_tensor * dst); +/** + * @brief Computes the L2 Normalization for a ggml tensor using the CANN + * backend. + * + * @details This function applies the L2 Normalization operation on the + * input tensor `src` and stores the result in the destination tensor + * `dst`. L2 Normalization scales the input tensor such that the + * L2 norm along the specified dimension equals 1. This operation + * is commonly used in neural networks for feature normalization + * and vector scaling. + * The operation is defined as: + * \f[ + * \text{out} = \frac{x}{\sqrt{\sum{x^2}}} + * \f] + * The normalization is performed along the last dimension by default. + * + * @param ctx The CANN context used for operations. + * @param dst The destination tensor where the normalized values will be stored. + * @attention The normalization is performed along the last dimension of the + * input tensor by default. + */ +void ggml_cann_l2_norm(ggml_backend_cann_context & ctx, ggml_tensor * dst); + /** * @brief Computes the Group Normalization for a ggml tensor using the CANN * backend. diff --git a/ggml/src/ggml-cann/ggml-cann.cpp b/ggml/src/ggml-cann/ggml-cann.cpp index 51345742ee..9de9440ac6 100644 --- a/ggml/src/ggml-cann/ggml-cann.cpp +++ b/ggml/src/ggml-cann/ggml-cann.cpp @@ -1777,6 +1777,9 @@ static bool ggml_cann_compute_forward(ggml_backend_cann_context & ctx, struct gg case GGML_OP_GROUP_NORM: ggml_cann_group_norm(ctx, dst); break; + case GGML_OP_L2_NORM: + ggml_cann_l2_norm(ctx, dst); + break; case GGML_OP_CONCAT: ggml_cann_concat(ctx, dst); break; @@ -2515,6 +2518,7 @@ static bool ggml_backend_cann_supports_op(ggml_backend_dev_t dev, const ggml_ten // value of paddingW should be at most half of kernelW return (p0 <= (k0 / 2)) && (p1 <= (k1 / 2)); } + case GGML_OP_L2_NORM: case GGML_OP_DUP: case GGML_OP_SUM: case GGML_OP_IM2COL: diff --git a/ggml/src/ggml-cpu/ops.cpp b/ggml/src/ggml-cpu/ops.cpp index 5a272b9abc..9f1e5f8d64 100644 --- a/ggml/src/ggml-cpu/ops.cpp +++ b/ggml/src/ggml-cpu/ops.cpp @@ -7,8 +7,9 @@ #include "unary-ops.h" #include "vec.h" -#include +#include #include +#include // ggml_compute_forward_dup @@ -7682,24 +7683,24 @@ static void ggml_compute_forward_argsort_f32( ggml_sort_order order = (ggml_sort_order) ggml_get_op_params_i32(dst, 0); for (int64_t i = ith; i < nr; i += nth) { - int32_t * dst_data = (int32_t *)((char *) dst->data + i*nb1); const float * src_data = (float *)((char *) src0->data + i*nb01); + int32_t * dst_data = (int32_t *)((char *) dst->data + i*nb1); + for (int64_t j = 0; j < ne0; j++) { dst_data[j] = j; } - // C doesn't have a functional sort, so we do a bubble sort instead - for (int64_t j = 0; j < ne0; j++) { - for (int64_t k = j + 1; k < ne0; k++) { - if ((order == GGML_SORT_ORDER_ASC && src_data[dst_data[j]] > src_data[dst_data[k]]) || - (order == GGML_SORT_ORDER_DESC && src_data[dst_data[j]] < src_data[dst_data[k]])) { - int32_t tmp = dst_data[j]; - dst_data[j] = dst_data[k]; - dst_data[k] = tmp; - } - } + std::function cmp; + + // note: this might be causing memory allocations? ideally should be avoided if it's the case + switch (order) { + case GGML_SORT_ORDER_ASC: cmp = [src_data](int32_t a, int32_t b) { return src_data[a] < src_data[b]; }; break; + case GGML_SORT_ORDER_DESC: cmp = [src_data](int32_t a, int32_t b) { return src_data[a] > src_data[b]; }; break; + default: GGML_ABORT("invalid sort order"); } + + std::sort(dst_data, dst_data + ne0, cmp); } } diff --git a/ggml/src/ggml-cpu/repack.cpp b/ggml/src/ggml-cpu/repack.cpp index 8421c84ce0..274be146dc 100644 --- a/ggml/src/ggml-cpu/repack.cpp +++ b/ggml/src/ggml-cpu/repack.cpp @@ -1600,29 +1600,52 @@ template src[0]; const ggml_tensor * src1 = op->src[1]; ggml_tensor * dst = op; GGML_TENSOR_BINARY_OP_LOCALS - const void * src1_wdata = params->wdata; const size_t src1_col_stride = ggml_row_size(PARAM_TYPE, ne10); + GGML_ASSERT(ne03 == 1 && ne13 == 1); + GGML_ASSERT(ne12 % ne02 == 0); + const int64_t r2 = ne12 / ne02; + + const int64_t i12 = src1_start / ne1; + const int64_t i11 = src1_start - i12 * ne1; + + // Determine batch index + const int64_t i02 = i12 / r2; + + const int64_t i1 = i11; + const int64_t i2 = i12; + + const char * src0_ptr = (const char *) src0->data + i02 * nb02; + const char * src1_ptr = (const char *) params->wdata + (i11 + i12 * ne11) * src1_col_stride; + char * dst_ptr = ((char *) dst->data + (i1 * nb1 + i2 * nb2)); + + const int64_t nrows = src1_end - src1_start; + const int64_t ncols = src0_end - src0_start; + + GGML_ASSERT(src1_ptr + src1_col_stride * nrows <= (const char *) params->wdata + params->wsize); + // If there are more than three rows in src1, use gemm; otherwise, use gemv. - if (ne11 > 3) { - gemm(ne00, - (float *) ((char *) dst->data) + src0_start, ne01, - (const char *) src0->data + src0_start * nb01, - (const char *) src1_wdata, ne11 - ne11 % 4, src0_end - src0_start); + if (nrows > 3) { + gemm(ne00, (float *) (dst_ptr) + src0_start, nb1 / nb0, + src0_ptr + src0_start * nb01, src1_ptr, + nrows - (nrows % 4), ncols); } - for (int iter = ne11 - ne11 % 4; iter < ne11; iter++) { - gemv(ne00, - (float *) ((char *) dst->data + (iter * nb1)) + src0_start, ne01, - (const char *) src0->data + src0_start * nb01, - (const char *) src1_wdata + (src1_col_stride * iter), 1, - src0_end - src0_start); + for (int iter = nrows - (nrows % 4); iter < nrows; iter++) { + gemv(ne00, (float *) (dst_ptr + (iter * nb1)) + src0_start, + ne01, src0_ptr + src0_start * nb01, + src1_ptr + (src1_col_stride * iter), 1 /* nrows */, ncols); } } @@ -1647,6 +1670,12 @@ template type == GGML_TYPE_F32); GGML_ASSERT(ggml_n_dims(op->src[0]) == 2); @@ -1654,47 +1683,60 @@ template (params->wdata); const size_t nbw1 = ggml_row_size(PARAM_TYPE, ne10); + const size_t nbw2 = nbw1 * ne11; - assert(params->wsize >= nbw1 * ne11); + assert(params->wsize >= nbw2 * ne12); const ggml_from_float_t from_float = ggml_get_type_traits_cpu(PARAM_TYPE)->from_float; - int64_t i11_processed = 0; - for (int64_t i11 = ith * 4; i11 < ne11 - ne11 % 4; i11 += nth * 4) { - ggml_quantize_mat_t((float *) ((char *) src1->data + i11 * nb11), (void *) (wdata + i11 * nbw1), 4, ne10); - } + for (int64_t i12 = 0; i12 < ne12; i12++) { + char * data_ptr = (char *) src1->data + i12 * nb12; + char * wdata_ptr = wdata + i12 * nbw2; - i11_processed = ne11 - ne11 % 4; - for (int64_t i11 = i11_processed + ith; i11 < ne11; i11 += nth) { - from_float((float *) ((char *) src1->data + i11 * nb11), (void *) (wdata + i11 * nbw1), ne10); + for (int64_t i11 = ith * 4; i11 < ne11 - ne11 % 4; i11 += nth * 4) { + ggml_quantize_mat_t((float *) (data_ptr + i11 * nb11), + (void *) (wdata_ptr + i11 * nbw1), 4, ne10); + } + + const int64_t i11_processed = ne11 - ne11 % 4; + for (int64_t i11 = i11_processed + ith; i11 < ne11; i11 += nth) { + from_float((float *) (data_ptr + i11 * nb11), (void *) (wdata_ptr + i11 * nbw1), ne10); + } } // disable for NUMA const bool disable_chunking = ggml_is_numa(); // 4x chunks per thread - int64_t nr = ggml_nrows(op->src[0]); - int nth_scaled = nth * 4; - int64_t chunk_size = (nr + nth_scaled - 1) / nth_scaled; - int64_t nchunk = (nr + chunk_size - 1) / chunk_size; + const int64_t nr0 = ggml_nrows(op->src[0]); + const int64_t nr1 = ne1 * ne2 * ne3; + + int nth_scaled = nth * 4; + int64_t chunk_size0 = (nr0 + nth_scaled - 1) / nth_scaled; + // avoid too small chunks for narrow src1 + int64_t chunk_size1 = MAX(16, (nr1 + nth - 1) / nth); + int64_t nchunk0 = (nr0 + chunk_size0 - 1) / chunk_size0; + int64_t nchunk1 = (nr1 + chunk_size1 - 1) / chunk_size1; // Ensure minimum chunk size to avoid alignment issues with high thread counts // Minimum chunk size should be at least NB_COLS to prevent overlapping chunks after alignment const int64_t min_chunk_size = NB_COLS; - if (nchunk > 0 && (nr / nchunk) < min_chunk_size && nr >= min_chunk_size) { - nchunk = (nr + min_chunk_size - 1) / min_chunk_size; + if (nchunk0 > 0 && (nr0 / nchunk0) < min_chunk_size && nr0 >= min_chunk_size) { + nchunk0 = (nr0 + min_chunk_size - 1) / min_chunk_size; } - if (nth == 1 || nchunk < nth || disable_chunking) { - nchunk = nth; + if (nth == 1 || nchunk0 * nchunk1 < nth || disable_chunking) { + nchunk0 = nr0 > nr1 ? nth : 1; + nchunk1 = nr0 > nr1 ? 1 : nth; } + const int64_t dr0 = (nr0 + nchunk0 - 1) / nchunk0; + const int64_t dr1 = (nr1 + nchunk1 - 1) / nchunk1; + // Ensure nchunk doesn't exceed the number of rows divided by minimum chunk size // This prevents creating too many tiny chunks that could overlap after alignment - const int64_t max_nchunk = (nr + min_chunk_size - 1) / min_chunk_size; - if (nchunk > max_nchunk) { - nchunk = max_nchunk; - } + const int64_t max_nchunk = (nr0 + min_chunk_size - 1) / min_chunk_size; + nchunk0 = MIN(nchunk0, max_nchunk); if (ith == 0) { // Every thread starts at ith, so the first unprocessed chunk is nth. This save a bit of coordination right at the start. @@ -1706,23 +1748,29 @@ template ne01) { - src0_end = ne01; - } + src0_end = (src0_end % NB_COLS) ? src0_end + NB_COLS - (src0_end % NB_COLS) : src0_end; + src0_end = MIN(src0_end, ne01); + // Make sure current plane is the last one before exiting if (src0_start >= src0_end) { - break; + current_chunk = ggml_threadpool_chunk_add(params->threadpool, 1); + continue; } - forward_mul_mat_one_chunk(params, dst, src0_start, src0_end); + forward_mul_mat_one_chunk(params, dst, src0_start, src0_end, src1_start, src1_end); current_chunk = ggml_threadpool_chunk_add(params->threadpool, 1); } diff --git a/ggml/src/ggml-hexagon/ggml-hexagon.cpp b/ggml/src/ggml-hexagon/ggml-hexagon.cpp index 7064b7486f..cabd301ad3 100644 --- a/ggml/src/ggml-hexagon/ggml-hexagon.cpp +++ b/ggml/src/ggml-hexagon/ggml-hexagon.cpp @@ -3156,26 +3156,17 @@ static inline bool op_reuse_src1(const ggml_tensor * op1, const ggml_tensor * op return (op0 && op0->src[1] == op1->src[1]); } +static inline bool is_compute_op(ggml_tensor *node) +{ + return !(ggml_op_is_empty(node->op) || ggml_is_empty(node)); +} + // scan the graph and figure out last compute op index static inline int last_compute_op(ggml_cgraph * graph) { - int last; + int last = 0; for (int i = 0; i < graph->n_nodes; ++i) { - ggml_tensor * node = graph->nodes[i]; - - switch (node->op) { - case GGML_OP_MUL_MAT: - case GGML_OP_MUL_MAT_ID: - case GGML_OP_MUL: - case GGML_OP_ADD: - case GGML_OP_SUB: - case GGML_OP_RMS_NORM: - case GGML_OP_GLU: - case GGML_OP_ADD_ID: - last = i; - break; - - default: - break; + if (is_compute_op(graph->nodes[i])) { + last = i; } } @@ -3194,6 +3185,10 @@ static ggml_status ggml_backend_hexagon_graph_compute(ggml_backend_t backend, gg for (int i = 0; i < graph->n_nodes; ++i) { ggml_tensor * node = graph->nodes[i]; + if (!is_compute_op(node)) { + continue; + } + uint32_t flags = 0; // skip quantizer if src1 is reused @@ -3245,14 +3240,6 @@ static ggml_status ggml_backend_hexagon_graph_compute(ggml_backend_t backend, gg ggml_hexagon_rope(node, flags); break; - // non-compute ops - case GGML_OP_NONE: - case GGML_OP_RESHAPE: - case GGML_OP_VIEW: - case GGML_OP_PERMUTE: - case GGML_OP_TRANSPOSE: - break; - default: GGML_ABORT("\nggml-hex: graph-compute %s is not supported\n", ggml_op_desc(node)); } diff --git a/ggml/src/ggml-hexagon/htp/binary-ops.c b/ggml/src/ggml-hexagon/htp/binary-ops.c index 92c0109d28..8ed7f67d9c 100644 --- a/ggml/src/ggml-hexagon/htp/binary-ops.c +++ b/ggml/src/ggml-hexagon/htp/binary-ops.c @@ -34,6 +34,11 @@ static hvx_elemwise_f32_func func_table_HVX[] = { hvx_mul_f32, hvx_add_f32, static hvx_elemwise_f32_func func_table_HVX_opt[] = { hvx_mul_f32_opt, hvx_add_f32_opt, hvx_sub_f32_opt }; #define htp_binary_preamble \ + const struct htp_tensor * src0 = &octx->src0; \ + const struct htp_tensor * src1 = &octx->src1; \ + const struct htp_tensor * src2 = &octx->src2; \ + struct htp_tensor * dst = &octx->dst; \ + \ const uint32_t ne00 = src0->ne[0]; \ const uint32_t ne01 = src0->ne[1]; \ const uint32_t ne02 = src0->ne[2]; \ @@ -62,16 +67,15 @@ static hvx_elemwise_f32_func func_table_HVX_opt[] = { hvx_mul_f32_opt, hvx_add_f const uint32_t nb0 = dst->nb[0]; \ const uint32_t nb1 = dst->nb[1]; \ const uint32_t nb2 = dst->nb[2]; \ - const uint32_t nb3 = dst->nb[3]; - -static void binary_job_f32_per_thread(const struct htp_tensor * src0, - const struct htp_tensor * src1, - struct htp_tensor * dst, - uint8_t * spad_data, - uint32_t nth, - uint32_t ith, - uint32_t src0_nrows_per_thread, - enum htp_op op) { + const uint32_t nb3 = dst->nb[3]; \ + \ + const uint32_t src0_nrows_per_thread = octx->src0_nrows_per_thread; + +static void binary_job_f32_per_thread(struct htp_ops_context * octx, + uint8_t * spad_data, + uint32_t nth, + uint32_t ith, + enum htp_op op) { htp_binary_preamble; const size_t src0_row_size = nb01; @@ -107,16 +111,23 @@ static void binary_job_f32_per_thread(const struct htp_tensor * src0, uint8_t * restrict spad_data_th = spad_data + (ith * src0_row_size); - const uint32_t nr0 = ne00 / ne10; - const uint8_t * restrict src0_ptr = (const uint8_t *) src0->data + (src0_start_row * src0_row_size); uint8_t * restrict dst_ptr = (uint8_t *) dst->data + (src0_start_row * dst_row_size); const uint8_t * restrict data_src1 = (const uint8_t *) src1->data; - const uint8_t * restrict src1_ptr = NULL; + + const uint32_t ne02_ne01 = ne02 * ne01; for (uint32_t ir = src0_start_row; ir < src0_end_row; ir++) { - src1_ptr = data_src1 + (ir % src1_nrows) * src1_row_size; + const uint32_t i03 = fastdiv(ir, &octx->src0_div21); + const uint32_t i02 = fastdiv(ir - i03 * ne02_ne01, &octx->src0_div1); + const uint32_t i01 = (ir - i03 * ne02_ne01 - i02 * ne01); + + const uint32_t i13 = fastmodulo(i03, ne13, &octx->src1_div3); + const uint32_t i12 = fastmodulo(i02, ne12, &octx->src1_div2); + const uint32_t i11 = fastmodulo(i01, ne11, &octx->src1_div1); + + const uint8_t * restrict src1_ptr = data_src1 + i13 * nb13 + i12 * nb12 + i11 * src1_row_size; if (ir + 1 < src0_end_row) { htp_l2fetch(src0_ptr + ne00, 1, src0_row_size, src0_row_size); @@ -125,6 +136,7 @@ static void binary_job_f32_per_thread(const struct htp_tensor * src0, } } + const uint32_t nr0 = ne00 / ne10; if (nr0 > 1) { if ((1 == is_aligned) && (nr0 == ne00)) { hvx_bcast_fp32_a(spad_data_th, *(float *) src1_ptr, nr0); @@ -149,22 +161,17 @@ static void binary_job_f32_per_thread(const struct htp_tensor * src0, (unsigned) HAP_perf_qtimer_count_to_us(t2 - t1)); } -static void binary_add_id_job_f32_per_thread(const struct htp_tensor * src0, - const struct htp_tensor * src1, - const struct htp_tensor * src2, - struct htp_tensor * dst, - uint8_t * spad_data, - uint32_t nth, - uint32_t ith, - uint32_t src0_nrows_per_thread, - hvx_elemwise_f32_func func_HVX) { +static void binary_add_id_job_f32_per_thread(struct htp_ops_context * octx, + uint8_t * spad_data, + uint32_t nth, + uint32_t ith, + hvx_elemwise_f32_func func_HVX) { htp_binary_preamble; const size_t src0_row_size = nb01; const size_t src1_row_size = nb11; const size_t dst_row_size = nb1; - const uint32_t ne02_ne01 = ne02 * ne01; const uint32_t src0_nrows = ne01 * ne02 * ne03; // src0 rows const uint32_t src0_start_row = src0_nrows_per_thread * ith; @@ -187,10 +194,11 @@ static void binary_add_id_job_f32_per_thread(const struct htp_tensor * src0, const uint8_t * restrict data_src1 = (const uint8_t *) src1->data; uint8_t * restrict data_dst = (uint8_t *) dst->data; + const uint32_t ne02_ne01 = ne02 * ne01; for (uint32_t ir = src0_start_row; ir < src0_end_row; ir++) { // src0 indices - const uint32_t i03 = ir / ne02_ne01; - const uint32_t i02 = (ir - i03 * ne02_ne01) / ne01; + const uint32_t i03 = fastdiv(ir, &octx->src0_div21); + const uint32_t i02 = fastdiv(ir - i03 * ne02_ne01, &octx->src0_div1); const uint32_t i01 = (ir - i03 * ne02_ne01 - i02 * ne01); // src1 indices @@ -234,13 +242,11 @@ static void binary_job_dispatcher_f32(unsigned int n, unsigned int i, void * dat case HTP_OP_MUL: case HTP_OP_ADD: case HTP_OP_SUB: - binary_job_f32_per_thread(&octx->src0, &octx->src1, &octx->dst, octx->src1_spad.data, n, i, - octx->src0_nrows_per_thread, octx->op); + binary_job_f32_per_thread(octx, octx->src1_spad.data, n, i, octx->op); break; case HTP_OP_ADD_ID: - binary_add_id_job_f32_per_thread(&octx->src0, &octx->src1, &octx->src2, &octx->dst, octx->src0_spad.data, n, - i, octx->src0_nrows_per_thread, hvx_add_f32); + binary_add_id_job_f32_per_thread(octx, octx->src0_spad.data, n, i, hvx_add_f32); break; default: @@ -321,6 +327,16 @@ static int execute_op_binary_f32(struct htp_ops_context * octx) { octx->src0_nrows_per_thread = (src0_nrows + n_jobs - 1) / n_jobs; + octx->src0_div21 = init_fastdiv_values(src0->ne[2] * src0->ne[1]); + octx->src0_div3 = init_fastdiv_values(src0->ne[3]); + octx->src0_div2 = init_fastdiv_values(src0->ne[2]); + octx->src0_div1 = init_fastdiv_values(src0->ne[1]); + + octx->src1_div21 = init_fastdiv_values(src1->ne[2] * src1->ne[1]); + octx->src1_div3 = init_fastdiv_values(src1->ne[3]); + octx->src1_div2 = init_fastdiv_values(src1->ne[2]); + octx->src1_div1 = init_fastdiv_values(src1->ne[1]); + worker_pool_run_func(octx->ctx->worker_pool, binary_op_func, octx, n_jobs); } diff --git a/ggml/src/ggml-hexagon/htp/htp-msg.h b/ggml/src/ggml-hexagon/htp/htp-msg.h index f23d578806..9278f41f4e 100644 --- a/ggml/src/ggml-hexagon/htp/htp-msg.h +++ b/ggml/src/ggml-hexagon/htp/htp-msg.h @@ -119,10 +119,10 @@ static const char * htp_type_name(uint32_t t) { #define HTP_MAX_DIMS 4 struct htp_tensor { - uint32_t data; // Buffer offset in the messages, and data pointer on the NSP - uint32_t type; // Data type - uint32_t ne[HTP_MAX_DIMS]; // Number of elements - uint32_t nb[HTP_MAX_DIMS]; // Stride in bytes (see ggml.h ggml_tensor) + uint32_t data; // Buffer offset in the messages, and data pointer on the NSP + uint32_t type; // Data type + uint32_t ne[HTP_MAX_DIMS]; // Number of elements + uint32_t nb[HTP_MAX_DIMS]; // Stride in bytes (see ggml.h ggml_tensor) }; #define HTP_MAX_OP_PARAMS 64 diff --git a/ggml/src/ggml-hexagon/htp/htp-ops.h b/ggml/src/ggml-hexagon/htp/htp-ops.h index 4572319679..e87657436f 100644 --- a/ggml/src/ggml-hexagon/htp/htp-ops.h +++ b/ggml/src/ggml-hexagon/htp/htp-ops.h @@ -4,6 +4,7 @@ #include "htp-ctx.h" #include "htp-msg.h" #include "worker-pool.h" +#include "ops-utils.h" #include #include @@ -38,6 +39,16 @@ struct htp_ops_context { uint32_t src0_nrows_per_thread; uint32_t src1_nrows_per_thread; + struct fastdiv_values src0_div1; // fastdiv values for ne1 + struct fastdiv_values src0_div2; // fastdiv values for ne2 + struct fastdiv_values src0_div3; // fastdiv values for ne3 + struct fastdiv_values src0_div21; // fastdiv values for ne2 * ne1 + + struct fastdiv_values src1_div1; // fastdiv values for ne1 + struct fastdiv_values src1_div2; // fastdiv values for ne2 + struct fastdiv_values src1_div3; // fastdiv values for ne3 + struct fastdiv_values src1_div21; // fastdiv values for ne2 * ne1 + uint32_t flags; }; diff --git a/ggml/src/ggml-hexagon/htp/ops-utils.h b/ggml/src/ggml-hexagon/htp/ops-utils.h index 302f162521..af9c3305f6 100644 --- a/ggml/src/ggml-hexagon/htp/ops-utils.h +++ b/ggml/src/ggml-hexagon/htp/ops-utils.h @@ -31,6 +31,39 @@ static inline uint32_t htp_round_up(uint32_t n, uint32_t m) { return m * ((n + m - 1) / m); } +// See https://gmplib.org/~tege/divcnst-pldi94.pdf figure 4.1. +// Precompute mp (m' in the paper) and L such that division +// can be computed using a multiply (high 32b of 64b result) +// and a shift: +// +// n/d = (mulhi(n, mp) + n) >> L; +struct fastdiv_values { + uint32_t mp; + uint32_t l; +}; + +static inline struct fastdiv_values init_fastdiv_values(uint32_t d) { + struct fastdiv_values result = { 0, 0 }; + // compute L = ceil(log2(d)); + while (result.l < 32 && ((uint32_t) 1 << result.l) < d) { + ++(result.l); + } + + result.mp = (uint32_t) (((uint64_t) 1 << 32) * (((uint64_t) 1 << result.l) - d) / d + 1); + return result; +} + +static inline uint32_t fastdiv(uint32_t n, const struct fastdiv_values * vals) { + // Compute high 32 bits of n * mp + const uint32_t hi = (uint32_t) (((uint64_t) n * vals->mp) >> 32); // mulhi(n, mp) + // add n, apply bit shift + return (hi + n) >> vals->l; +} + +static inline uint32_t fastmodulo(uint32_t n, uint32_t d, const struct fastdiv_values * vals) { + return n - fastdiv(n, vals) * d; +} + static inline void htp_l2fetch(const void * p, uint32_t height, uint32_t width, uint32_t stride) { const uint64_t control = Q6_P_combine_RR(stride, Q6_R_combine_RlRl(width, height)); asm volatile(" l2fetch(%0,%1) " : : "r"(p), "r"(control)); diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cpp index f3b3e36574..941fd41c0d 100644 --- a/ggml/src/ggml-sycl/ggml-sycl.cpp +++ b/ggml/src/ggml-sycl/ggml-sycl.cpp @@ -3933,6 +3933,7 @@ static bool ggml_sycl_compute_forward(ggml_backend_sycl_context & ctx, struct gg break; case GGML_OP_SSM_CONV: ggml_sycl_ssm_conv(ctx, dst); + break; case GGML_OP_ROLL: ggml_sycl_roll(ctx, dst); break; diff --git a/scripts/sync_vendor.py b/scripts/sync_vendor.py index b578cf1e6a..4a89d08f80 100755 --- a/scripts/sync_vendor.py +++ b/scripts/sync_vendor.py @@ -12,9 +12,11 @@ "https://raw.githubusercontent.com/nothings/stb/refs/heads/master/stb_image.h": "vendor/stb/stb_image.h", - "https://github.com/mackron/miniaudio/raw/refs/tags/0.11.22/miniaudio.h": "vendor/miniaudio/miniaudio.h", + # not using latest tag to avoid this issue: https://github.com/ggml-org/llama.cpp/pull/17179#discussion_r2515877926 + # "https://github.com/mackron/miniaudio/raw/refs/tags/0.11.23/miniaudio.h": "vendor/miniaudio/miniaudio.h", + "https://github.com/mackron/miniaudio/raw/669ed3e844524fcd883231b13095baee9f6de304/miniaudio.h": "vendor/miniaudio/miniaudio.h", - "https://raw.githubusercontent.com/yhirose/cpp-httplib/refs/tags/v0.20.1/httplib.h": "vendor/cpp-httplib/httplib.h", + "https://raw.githubusercontent.com/yhirose/cpp-httplib/refs/tags/v0.27.0/httplib.h": "vendor/cpp-httplib/httplib.h", } for url, filename in vendor.items(): diff --git a/tools/server/CMakeLists.txt b/tools/server/CMakeLists.txt index 5f8a50320d..c801e84c3d 100644 --- a/tools/server/CMakeLists.txt +++ b/tools/server/CMakeLists.txt @@ -7,6 +7,10 @@ if (MINGW) add_compile_definitions(_WIN32_WINNT=${GGML_WIN_VER}) endif() +if (NOT LLAMA_HTTPLIB) + message(FATAL_ERROR "LLAMA_HTTPLIB is OFF, cannot build llama-server. Hint: to skip building server, set -DLLAMA_BUILD_SERVER=OFF") +endif() + set(TARGET_SRCS server.cpp utils.hpp diff --git a/tools/server/server.cpp b/tools/server/server.cpp index 6bd4be3cc1..0b3c77879c 100644 --- a/tools/server/server.cpp +++ b/tools/server/server.cpp @@ -684,7 +684,7 @@ struct server_task_result { } virtual bool is_stop() { // only used by server_task_result_cmpl_* - return false; + return true; } virtual int get_index() { return -1; @@ -3238,105 +3238,6 @@ struct server_context { queue_results.send(std::move(res)); } - // - // Functions to create new task(s) and receive result(s) - // - - void cancel_tasks(const std::unordered_set & id_tasks) { - std::vector cancel_tasks; - cancel_tasks.reserve(id_tasks.size()); - for (const auto & id_task : id_tasks) { - SRV_WRN("cancel task, id_task = %d\n", id_task); - - server_task task(SERVER_TASK_TYPE_CANCEL); - task.id_target = id_task; - queue_results.remove_waiting_task_id(id_task); - cancel_tasks.push_back(std::move(task)); - } - // push to beginning of the queue, so it has highest priority - queue_tasks.post(std::move(cancel_tasks), true); - } - - // receive the results from task(s) - void receive_multi_results( - const std::unordered_set & id_tasks, - const std::function&)> & result_handler, - const std::function & error_handler, - const std::function & is_connection_closed) { - std::vector results(id_tasks.size()); - for (int i = 0; i < (int)id_tasks.size(); i++) { - server_task_result_ptr result = queue_results.recv_with_timeout(id_tasks, HTTP_POLLING_SECONDS); - - if (is_connection_closed()) { - cancel_tasks(id_tasks); - return; - } - - if (result == nullptr) { - i--; // retry - continue; - } - - if (result->is_error()) { - error_handler(result->to_json()); - cancel_tasks(id_tasks); - return; - } - - GGML_ASSERT( - dynamic_cast(result.get()) != nullptr - || dynamic_cast(result.get()) != nullptr - || dynamic_cast(result.get()) != nullptr - ); - const size_t idx = result->get_index(); - GGML_ASSERT(idx < results.size() && "index out of range"); - results[idx] = std::move(result); - } - result_handler(results); - } - - // receive the results from task(s), in stream mode - void receive_cmpl_results_stream( - const std::unordered_set & id_tasks, - const std::function & result_handler, - const std::function & error_handler, - const std::function & is_connection_closed) { - size_t n_finished = 0; - while (true) { - server_task_result_ptr result = queue_results.recv_with_timeout(id_tasks, HTTP_POLLING_SECONDS); - - if (is_connection_closed()) { - cancel_tasks(id_tasks); - return; - } - - if (result == nullptr) { - continue; // retry - } - - if (result->is_error()) { - error_handler(result->to_json()); - cancel_tasks(id_tasks); - return; - } - - GGML_ASSERT( - dynamic_cast(result.get()) != nullptr - || dynamic_cast(result.get()) != nullptr - ); - if (!result_handler(result)) { - cancel_tasks(id_tasks); - break; - } - - if (result->is_stop()) { - if (++n_finished == id_tasks.size()) { - break; - } - } - } - } - // // Functions to process the task // @@ -4418,6 +4319,104 @@ struct server_context { } }; +// generator-like API for server responses, support pooling connection state and aggregating results +struct server_response_reader { + std::unordered_set id_tasks; + server_context & ctx_server; + size_t received_count = 0; + bool cancelled = false; + + server_response_reader(server_context & ctx_server) : ctx_server(ctx_server) {} + ~server_response_reader() { + stop(); + } + + void post_tasks(std::vector && tasks) { + id_tasks = server_task::get_list_id(tasks); + ctx_server.queue_results.add_waiting_tasks(tasks); + ctx_server.queue_tasks.post(std::move(tasks)); + } + + bool has_next() { + return !cancelled && received_count < id_tasks.size(); + } + + // return nullptr if should_stop() is true before receiving a result + // note: if one error is received, it will stop further processing and return error result + server_task_result_ptr next(const std::function & should_stop) { + while (true) { + server_task_result_ptr result = ctx_server.queue_results.recv_with_timeout(id_tasks, HTTP_POLLING_SECONDS); + if (result == nullptr) { + // timeout, check stop condition + if (should_stop()) { + SRV_DBG("%s", "stopping wait for next result due to should_stop condition\n"); + return nullptr; + } + } else { + if (result->is_error()) { + stop(); // cancel remaining tasks + SRV_DBG("%s", "received error result, stopping further processing\n"); + return result; + } + if (result->is_stop()) { + received_count++; + } + return result; + } + } + + // should not reach here + } + + struct batch_response { + bool is_terminated = false; // if true, indicates that processing was stopped before all results were received + std::vector results; + server_task_result_ptr error; // nullptr if no error + }; + + batch_response wait_for_all(const std::function & should_stop) { + batch_response batch_res; + batch_res.results.resize(id_tasks.size()); + while (has_next()) { + auto res = next(should_stop); + if (res == nullptr) { + batch_res.is_terminated = true; + return batch_res; + } + if (res->is_error()) { + batch_res.error = std::move(res); + return batch_res; + } + const size_t idx = res->get_index(); + GGML_ASSERT(idx < batch_res.results.size() && "index out of range"); + GGML_ASSERT(batch_res.results[idx] == nullptr && "duplicate result received"); + batch_res.results[idx] = std::move(res); + } + return batch_res; + } + + void stop() { + ctx_server.queue_results.remove_waiting_task_ids(id_tasks); + if (has_next() && !cancelled) { + // if tasks is not finished yet, cancel them + cancelled = true; + std::vector cancel_tasks; + cancel_tasks.reserve(id_tasks.size()); + for (const auto & id_task : id_tasks) { + SRV_WRN("cancel task, id_task = %d\n", id_task); + server_task task(SERVER_TASK_TYPE_CANCEL); + task.id_target = id_task; + ctx_server.queue_results.remove_waiting_task_id(id_task); + cancel_tasks.push_back(std::move(task)); + } + // push to beginning of the queue, so it has highest priority + ctx_server.queue_tasks.post(std::move(cancel_tasks), true); + } else { + SRV_DBG("%s", "all tasks already finished, no need to cancel\n"); + } + } +}; + static void log_server_request(const httplib::Request & req, const httplib::Response & res) { // skip GH copilot requests when using default port if (req.path == "/v1/health") { @@ -4432,6 +4431,17 @@ static void log_server_request(const httplib::Request & req, const httplib::Resp SRV_DBG("response: %s\n", res.body.c_str()); } +static void res_error(httplib::Response & res, const json & error_data) { + json final_response {{"error", error_data}}; + res.set_content(safe_json_to_str(final_response), MIMETYPE_JSON); + res.status = json_value(error_data, "code", 500); +} + +static void res_ok(httplib::Response & res, const json & data) { + res.set_content(safe_json_to_str(data), MIMETYPE_JSON); + res.status = 200; +} + std::function shutdown_handler; std::atomic_flag is_terminating = ATOMIC_FLAG_INIT; @@ -4501,19 +4511,7 @@ int main(int argc, char ** argv) { svr->set_default_headers({{"Server", "llama.cpp"}}); svr->set_logger(log_server_request); - - auto res_error = [](httplib::Response & res, const json & error_data) { - json final_response {{"error", error_data}}; - res.set_content(safe_json_to_str(final_response), MIMETYPE_JSON); - res.status = json_value(error_data, "code", 500); - }; - - auto res_ok = [](httplib::Response & res, const json & data) { - res.set_content(safe_json_to_str(data), MIMETYPE_JSON); - res.status = 200; - }; - - svr->set_exception_handler([&res_error](const httplib::Request &, httplib::Response & res, const std::exception_ptr & ep) { + svr->set_exception_handler([](const httplib::Request &, httplib::Response & res, const std::exception_ptr & ep) { std::string message; try { std::rethrow_exception(ep); @@ -4532,7 +4530,7 @@ int main(int argc, char ** argv) { } }); - svr->set_error_handler([&res_error](const httplib::Request &, httplib::Response & res) { + svr->set_error_handler([](const httplib::Request &, httplib::Response & res) { if (res.status == 404) { res_error(res, format_error_response("File Not Found", ERROR_TYPE_NOT_FOUND)); } @@ -4562,7 +4560,7 @@ int main(int argc, char ** argv) { // Middlewares // - auto middleware_validate_api_key = [¶ms, &res_error](const httplib::Request & req, httplib::Response & res) { + auto middleware_validate_api_key = [¶ms](const httplib::Request & req, httplib::Response & res) { static const std::unordered_set public_endpoints = { "/health", "/v1/health", @@ -4600,7 +4598,7 @@ int main(int argc, char ** argv) { return false; }; - auto middleware_server_state = [&res_error, &state](const httplib::Request & req, httplib::Response & res) { + auto middleware_server_state = [&state](const httplib::Request & req, httplib::Response & res) { server_state current_state = state.load(); if (current_state == SERVER_STATE_LOADING_MODEL) { auto tmp = string_split(req.path, '.'); @@ -4788,7 +4786,7 @@ int main(int argc, char ** argv) { res.status = 200; // HTTP OK }; - const auto handle_slots_save = [&ctx_server, &res_error, &res_ok, ¶ms](const httplib::Request & req, httplib::Response & res, int id_slot) { + const auto handle_slots_save = [&ctx_server, ¶ms](const httplib::Request & req, httplib::Response & res, int id_slot) { json request_data = json::parse(req.body); std::string filename = request_data.at("filename"); if (!fs_validate_filename(filename)) { @@ -4820,7 +4818,7 @@ int main(int argc, char ** argv) { res_ok(res, result->to_json()); }; - const auto handle_slots_restore = [&ctx_server, &res_error, &res_ok, ¶ms](const httplib::Request & req, httplib::Response & res, int id_slot) { + const auto handle_slots_restore = [&ctx_server, ¶ms](const httplib::Request & req, httplib::Response & res, int id_slot) { json request_data = json::parse(req.body); std::string filename = request_data.at("filename"); if (!fs_validate_filename(filename)) { @@ -4853,7 +4851,7 @@ int main(int argc, char ** argv) { res_ok(res, result->to_json()); }; - const auto handle_slots_erase = [&ctx_server, &res_error, &res_ok](const httplib::Request & /* req */, httplib::Response & res, int id_slot) { + const auto handle_slots_erase = [&ctx_server](const httplib::Request & /* req */, httplib::Response & res, int id_slot) { int task_id = ctx_server.queue_tasks.get_new_id(); { server_task task(SERVER_TASK_TYPE_SLOT_ERASE); @@ -4876,7 +4874,7 @@ int main(int argc, char ** argv) { res_ok(res, result->to_json()); }; - const auto handle_slots_action = [¶ms, &res_error, &handle_slots_save, &handle_slots_restore, &handle_slots_erase](const httplib::Request & req, httplib::Response & res) { + const auto handle_slots_action = [¶ms, &handle_slots_save, &handle_slots_restore, &handle_slots_erase](const httplib::Request & req, httplib::Response & res) { if (params.slot_save_path.empty()) { res_error(res, format_error_response("This server does not support slots action. Start it with `--slot-save-path`", ERROR_TYPE_NOT_SUPPORTED)); return; @@ -4905,7 +4903,7 @@ int main(int argc, char ** argv) { } }; - const auto handle_props = [¶ms, &ctx_server, &res_ok](const httplib::Request &, httplib::Response & res) { + const auto handle_props = [¶ms, &ctx_server](const httplib::Request &, httplib::Response & res) { json default_generation_settings_for_props; { @@ -4947,7 +4945,7 @@ int main(int argc, char ** argv) { res_ok(res, data); }; - const auto handle_props_change = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res) { + const auto handle_props_change = [&ctx_server](const httplib::Request & req, httplib::Response & res) { if (!ctx_server.params_base.endpoint_props) { res_error(res, format_error_response("This server does not support changing global properties. Start it with `--props`", ERROR_TYPE_NOT_SUPPORTED)); return; @@ -4960,7 +4958,7 @@ int main(int argc, char ** argv) { res_ok(res, {{ "success", true }}); }; - const auto handle_api_show = [&ctx_server, &res_ok](const httplib::Request &, httplib::Response & res) { + const auto handle_api_show = [&ctx_server](const httplib::Request &, httplib::Response & res) { bool has_mtmd = ctx_server.mctx != nullptr; json data = { { @@ -4991,7 +4989,7 @@ int main(int argc, char ** argv) { // handle completion-like requests (completion, chat, infill) // we can optionally provide a custom format for partial results and final results - const auto handle_completions_impl = [&ctx_server, &res_error, &res_ok]( + const auto handle_completions_impl = [&ctx_server]( server_task_type type, json & data, const std::vector & files, @@ -5001,7 +4999,10 @@ int main(int argc, char ** argv) { GGML_ASSERT(type == SERVER_TASK_TYPE_COMPLETION || type == SERVER_TASK_TYPE_INFILL); auto completion_id = gen_chatcmplid(); - std::unordered_set task_ids; + // need to store the reader as a pointer, so that it won't be destroyed when the handle returns + // use shared_ptr as it's shared between the chunked_content_provider() and on_complete() + const auto rd = std::make_shared(ctx_server); + try { std::vector tasks; @@ -5019,17 +5020,8 @@ int main(int argc, char ** argv) { // Everything else, including multimodal completions. inputs = tokenize_input_prompts(ctx_server.vocab, ctx_server.mctx, prompt, true, true); } - const size_t n_ctx_slot = ctx_server.slots.front().n_ctx; tasks.reserve(inputs.size()); for (size_t i = 0; i < inputs.size(); i++) { - auto n_prompt_tokens = inputs[i].size(); - if (n_prompt_tokens >= n_ctx_slot) { - json error_data = format_error_response("the request exceeds the available context size, try increasing it", ERROR_TYPE_EXCEED_CONTEXT_SIZE); - error_data["n_prompt_tokens"] = n_prompt_tokens; - error_data["n_ctx"] = n_ctx_slot; - res_error(res, error_data); - return; - } server_task task = server_task(type); task.id = ctx_server.queue_tasks.get_new_id(); @@ -5050,9 +5042,7 @@ int main(int argc, char ** argv) { tasks.push_back(std::move(task)); } - task_ids = server_task::get_list_id(tasks); - ctx_server.queue_results.add_waiting_tasks(tasks); - ctx_server.queue_tasks.post(std::move(tasks)); + rd->post_tasks(std::move(tasks)); } catch (const std::exception & e) { res_error(res, format_error_response(e.what(), ERROR_TYPE_INVALID_REQUEST)); return; @@ -5061,54 +5051,95 @@ int main(int argc, char ** argv) { bool stream = json_value(data, "stream", false); if (!stream) { - ctx_server.receive_multi_results(task_ids, [&](std::vector & results) { - if (results.size() == 1) { - // single result - res_ok(res, results[0]->to_json()); - } else { - // multiple results (multitask) - json arr = json::array(); - for (auto & res : results) { - arr.push_back(res->to_json()); - } - res_ok(res, arr); + // non-stream, wait for the results + auto all_results = rd->wait_for_all(is_connection_closed); + if (all_results.is_terminated) { + return; // connection is closed + } else if (all_results.error) { + res_error(res, all_results.error->to_json()); + return; + } else { + json arr = json::array(); + for (auto & res : all_results.results) { + GGML_ASSERT(dynamic_cast(res.get()) != nullptr); + arr.push_back(res->to_json()); } - }, [&](const json & error_data) { - res_error(res, error_data); - }, is_connection_closed); + // if single request, return single object instead of array + res_ok(res, arr.size() == 1 ? arr[0] : arr); + } - ctx_server.queue_results.remove_waiting_task_ids(task_ids); } else { - const auto chunked_content_provider = [task_ids, &ctx_server, oaicompat](size_t, httplib::DataSink & sink) { - ctx_server.receive_cmpl_results_stream(task_ids, [&](server_task_result_ptr & result) -> bool { - json res_json = result->to_json(); - if (res_json.is_array()) { - for (const auto & res : res_json) { - if (!server_sent_event(sink, res)) { - // sending failed (HTTP connection closed), cancel the generation - return false; - } - } - return true; - } else { - return server_sent_event(sink, res_json); + // in streaming mode, the first error must be treated as non-stream response + // this is to match the OAI API behavior + // ref: https://github.com/ggml-org/llama.cpp/pull/16486#discussion_r2419657309 + server_task_result_ptr first_result = rd->next(is_connection_closed); + if (first_result == nullptr) { + return; // connection is closed + } else if (first_result->is_error()) { + res_error(res, first_result->to_json()); + return; + } else { + GGML_ASSERT( + dynamic_cast(first_result.get()) != nullptr + || dynamic_cast(first_result.get()) != nullptr + ); + } + + // next responses are streamed + json first_result_json = first_result->to_json(); + const auto chunked_content_provider = [first_result_json, rd, oaicompat](size_t, httplib::DataSink & sink) mutable -> bool { + // flush the first result as it's not an error + if (!first_result_json.empty()) { + if (!server_sent_event(sink, first_result_json)) { + sink.done(); + return false; // sending failed, go to on_complete() } - }, [&](const json & error_data) { - server_sent_event(sink, json{{"error", error_data}}); - }, [&sink]() { - // note: do not use req.is_connection_closed here because req is already destroyed - return !sink.is_writable(); - }); - if (oaicompat != OAICOMPAT_TYPE_NONE) { - static const std::string ev_done = "data: [DONE]\n\n"; - sink.write(ev_done.data(), ev_done.size()); + first_result_json.clear(); // mark as sent } - sink.done(); - return false; + + // receive subsequent results + auto result = rd->next([&sink]{ return !sink.is_writable(); }); + if (result == nullptr) { + sink.done(); + return false; // connection is closed, go to on_complete() + } + + // send the results + json res_json = result->to_json(); + bool ok = false; + if (result->is_error()) { + ok = server_sent_event(sink, json {{ "error", result->to_json() }}); + sink.done(); + return false; // go to on_complete() + } else { + GGML_ASSERT( + dynamic_cast(result.get()) != nullptr + || dynamic_cast(result.get()) != nullptr + ); + ok = server_sent_event(sink, res_json); + } + + if (!ok) { + sink.done(); + return false; // sending failed, go to on_complete() + } + + // check if there is more data + if (!rd->has_next()) { + if (oaicompat != OAICOMPAT_TYPE_NONE) { + static const std::string ev_done = "data: [DONE]\n\n"; + sink.write(ev_done.data(), ev_done.size()); + } + sink.done(); + return false; // no more data, go to on_complete() + } + + // has next data, continue + return true; }; - auto on_complete = [task_ids, &ctx_server] (bool) { - ctx_server.queue_results.remove_waiting_task_ids(task_ids); + auto on_complete = [rd](bool) { + rd->stop(); }; res.set_chunked_content_provider("text/event-stream", chunked_content_provider, on_complete); @@ -5139,7 +5170,7 @@ int main(int argc, char ** argv) { OAICOMPAT_TYPE_COMPLETION); }; - const auto handle_infill = [&ctx_server, &res_error, &handle_completions_impl](const httplib::Request & req, httplib::Response & res) { + const auto handle_infill = [&ctx_server, &handle_completions_impl](const httplib::Request & req, httplib::Response & res) { // check model compatibility std::string err; if (llama_vocab_fim_pre(ctx_server.vocab) == LLAMA_TOKEN_NULL) { @@ -5238,7 +5269,7 @@ int main(int argc, char ** argv) { }; // same with handle_chat_completions, but without inference part - const auto handle_apply_template = [&ctx_server, &res_ok](const httplib::Request & req, httplib::Response & res) { + const auto handle_apply_template = [&ctx_server](const httplib::Request & req, httplib::Response & res) { auto body = json::parse(req.body); std::vector files; // dummy, unused json data = oaicompat_chat_params_parse( @@ -5248,7 +5279,7 @@ int main(int argc, char ** argv) { res_ok(res, {{ "prompt", std::move(data.at("prompt")) }}); }; - const auto handle_models = [¶ms, &ctx_server, &state, &res_ok](const httplib::Request &, httplib::Response & res) { + const auto handle_models = [¶ms, &ctx_server, &state](const httplib::Request &, httplib::Response & res) { server_state current_state = state.load(); json model_meta = nullptr; if (current_state == SERVER_STATE_READY) { @@ -5293,7 +5324,7 @@ int main(int argc, char ** argv) { res_ok(res, models); }; - const auto handle_tokenize = [&ctx_server, &res_ok](const httplib::Request & req, httplib::Response & res) { + const auto handle_tokenize = [&ctx_server](const httplib::Request & req, httplib::Response & res) { const json body = json::parse(req.body); json tokens_response = json::array(); @@ -5334,7 +5365,7 @@ int main(int argc, char ** argv) { res_ok(res, data); }; - const auto handle_detokenize = [&ctx_server, &res_ok](const httplib::Request & req, httplib::Response & res) { + const auto handle_detokenize = [&ctx_server](const httplib::Request & req, httplib::Response & res) { const json body = json::parse(req.body); std::string content; @@ -5347,7 +5378,7 @@ int main(int argc, char ** argv) { res_ok(res, data); }; - const auto handle_embeddings_impl = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res, oaicompat_type oaicompat) { + const auto handle_embeddings_impl = [&ctx_server](const httplib::Request & req, httplib::Response & res, oaicompat_type oaicompat) { if (!ctx_server.params_base.embedding) { res_error(res, format_error_response("This server does not support embeddings. Start it with `--embeddings`", ERROR_TYPE_NOT_SUPPORTED)); return; @@ -5402,8 +5433,7 @@ int main(int argc, char ** argv) { // create and queue the task json responses = json::array(); - bool error = false; - std::unordered_set task_ids; + server_response_reader rd(ctx_server); { std::vector tasks; for (size_t i = 0; i < tokenized_prompts.size(); i++) { @@ -5419,27 +5449,23 @@ int main(int argc, char ** argv) { tasks.push_back(std::move(task)); } - - task_ids = server_task::get_list_id(tasks); - ctx_server.queue_results.add_waiting_tasks(tasks); - ctx_server.queue_tasks.post(std::move(tasks)); + rd.post_tasks(std::move(tasks)); } - // get the result - ctx_server.receive_multi_results(task_ids, [&](std::vector & results) { - for (auto & res : results) { + // wait for the results + auto all_results = rd.wait_for_all(req.is_connection_closed); + + // collect results + if (all_results.is_terminated) { + return; // connection is closed + } else if (all_results.error) { + res_error(res, all_results.error->to_json()); + return; + } else { + for (auto & res : all_results.results) { GGML_ASSERT(dynamic_cast(res.get()) != nullptr); responses.push_back(res->to_json()); } - }, [&](const json & error_data) { - res_error(res, error_data); - error = true; - }, req.is_connection_closed); - - ctx_server.queue_results.remove_waiting_task_ids(task_ids); - - if (error) { - return; } // write JSON response @@ -5457,7 +5483,7 @@ int main(int argc, char ** argv) { handle_embeddings_impl(req, res, OAICOMPAT_TYPE_EMBEDDING); }; - const auto handle_rerank = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res) { + const auto handle_rerank = [&ctx_server](const httplib::Request & req, httplib::Response & res) { if (!ctx_server.params_base.embedding || ctx_server.params_base.pooling_type != LLAMA_POOLING_TYPE_RANK) { res_error(res, format_error_response("This server does not support reranking. Start it with `--reranking`", ERROR_TYPE_NOT_SUPPORTED)); return; @@ -5493,8 +5519,7 @@ int main(int argc, char ** argv) { // create and queue the task json responses = json::array(); - bool error = false; - std::unordered_set task_ids; + server_response_reader rd(ctx_server); { std::vector tasks; tasks.reserve(documents.size()); @@ -5506,24 +5531,23 @@ int main(int argc, char ** argv) { task.tokens = std::move(tmp); tasks.push_back(std::move(task)); } - - task_ids = server_task::get_list_id(tasks); - ctx_server.queue_results.add_waiting_tasks(tasks); - ctx_server.queue_tasks.post(std::move(tasks)); + rd.post_tasks(std::move(tasks)); } - ctx_server.receive_multi_results(task_ids, [&](std::vector & results) { - for (auto & res : results) { + // wait for the results + auto all_results = rd.wait_for_all(req.is_connection_closed); + + // collect results + if (all_results.is_terminated) { + return; // connection is closed + } else if (all_results.error) { + res_error(res, all_results.error->to_json()); + return; + } else { + for (auto & res : all_results.results) { GGML_ASSERT(dynamic_cast(res.get()) != nullptr); responses.push_back(res->to_json()); } - }, [&](const json & error_data) { - res_error(res, error_data); - error = true; - }, req.is_connection_closed); - - if (error) { - return; } // write JSON response diff --git a/tools/server/utils.hpp b/tools/server/utils.hpp index e9d4431ddf..b1ecc5af5e 100644 --- a/tools/server/utils.hpp +++ b/tools/server/utils.hpp @@ -453,15 +453,29 @@ static std::string tokens_to_output_formatted_string(const llama_context * ctx, return out; } +// note: if data is a json array, it will be sent as multiple events, one per item static bool server_sent_event(httplib::DataSink & sink, const json & data) { - const std::string str = - "data: " + - data.dump(-1, ' ', false, json::error_handler_t::replace) + - "\n\n"; // required by RFC 8895 - A message is terminated by a blank line (two line terminators in a row). + static auto send_single = [](httplib::DataSink & sink, const json & data) -> bool { + const std::string str = + "data: " + + data.dump(-1, ' ', false, json::error_handler_t::replace) + + "\n\n"; // required by RFC 8895 - A message is terminated by a blank line (two line terminators in a row). + + LOG_DBG("data stream, to_send: %s", str.c_str()); + return sink.write(str.c_str(), str.size()); + }; - LOG_DBG("data stream, to_send: %s", str.c_str()); + if (data.is_array()) { + for (const auto & item : data) { + if (!send_single(sink, item)) { + return false; + } + } + } else { + return send_single(sink, data); + } - return sink.write(str.c_str(), str.size()); + return true; } // diff --git a/tools/server/webui/.storybook/preview.ts b/tools/server/webui/.storybook/preview.ts index fb91386af4..8d530e43e3 100644 --- a/tools/server/webui/.storybook/preview.ts +++ b/tools/server/webui/.storybook/preview.ts @@ -11,8 +11,16 @@ const preview: Preview = { date: /Date$/i } }, + backgrounds: { disable: true + }, + + a11y: { + // 'todo' - show a11y violations in the test UI only + // 'error' - fail CI on a11y violations + // 'off' - skip a11y checks entirely + test: 'todo' } }, decorators: [ diff --git a/tools/server/webui/.storybook/vitest.setup.ts b/tools/server/webui/.storybook/vitest.setup.ts index e0c1753c84..1471572898 100644 --- a/tools/server/webui/.storybook/vitest.setup.ts +++ b/tools/server/webui/.storybook/vitest.setup.ts @@ -1,8 +1,9 @@ +import * as a11yAddonAnnotations from '@storybook/addon-a11y/preview'; import { setProjectAnnotations } from '@storybook/sveltekit'; import * as previewAnnotations from './preview'; import { beforeAll } from 'vitest'; -const project = setProjectAnnotations([previewAnnotations]); +const project = setProjectAnnotations([a11yAddonAnnotations, previewAnnotations]); beforeAll(async () => { if (project.beforeAll) { diff --git a/tools/server/webui/package-lock.json b/tools/server/webui/package-lock.json index 8fab38f6f1..a11b87ad50 100644 --- a/tools/server/webui/package-lock.json +++ b/tools/server/webui/package-lock.json @@ -22,20 +22,20 @@ "unist-util-visit": "^5.0.0" }, "devDependencies": { - "@chromatic-com/storybook": "^4.0.1", + "@chromatic-com/storybook": "^4.1.2", "@eslint/compat": "^1.2.5", "@eslint/js": "^9.18.0", "@internationalized/date": "^3.8.2", "@lucide/svelte": "^0.515.0", "@playwright/test": "^1.49.1", - "@storybook/addon-a11y": "^9.0.17", - "@storybook/addon-docs": "^9.0.17", - "@storybook/addon-svelte-csf": "^5.0.7", - "@storybook/addon-vitest": "^9.0.17", - "@storybook/sveltekit": "^9.0.17", - "@sveltejs/adapter-static": "^3.0.8", - "@sveltejs/kit": "^2.22.0", - "@sveltejs/vite-plugin-svelte": "^6.0.0", + "@storybook/addon-a11y": "^10.0.7", + "@storybook/addon-docs": "^10.0.7", + "@storybook/addon-svelte-csf": "^5.0.10", + "@storybook/addon-vitest": "^10.0.7", + "@storybook/sveltekit": "^10.0.7", + "@sveltejs/adapter-static": "^3.0.10", + "@sveltejs/kit": "^2.48.4", + "@sveltejs/vite-plugin-svelte": "^6.2.1", "@tailwindcss/forms": "^0.5.9", "@tailwindcss/typography": "^0.5.15", "@tailwindcss/vite": "^4.0.0", @@ -46,21 +46,21 @@ "dexie": "^4.0.11", "eslint": "^9.18.0", "eslint-config-prettier": "^10.0.1", - "eslint-plugin-storybook": "^9.0.17", + "eslint-plugin-storybook": "^10.0.7", "eslint-plugin-svelte": "^3.0.0", "fflate": "^0.8.2", "globals": "^16.0.0", "http-server": "^14.1.1", "mdast": "^3.0.0", "mdsvex": "^0.12.3", - "playwright": "^1.53.0", + "playwright": "^1.56.1", "prettier": "^3.4.2", "prettier-plugin-svelte": "^3.3.3", "prettier-plugin-tailwindcss": "^0.6.11", "rehype-katex": "^7.0.1", "remark-math": "^6.0.0", "sass": "^1.93.3", - "storybook": "^9.0.17", + "storybook": "^10.0.7", "svelte": "^5.0.0", "svelte-check": "^4.0.0", "tailwind-merge": "^3.3.1", @@ -71,7 +71,7 @@ "typescript-eslint": "^8.20.0", "unified": "^11.0.5", "uuid": "^13.0.0", - "vite": "^7.0.4", + "vite": "^7.2.2", "vite-plugin-devtools-json": "^0.2.0", "vitest": "^3.2.3", "vitest-browser-svelte": "^0.1.0" @@ -133,9 +133,9 @@ } }, "node_modules/@chromatic-com/storybook": { - "version": "4.0.1", - "resolved": "https://registry.npmjs.org/@chromatic-com/storybook/-/storybook-4.0.1.tgz", - "integrity": "sha512-GQXe5lyZl3yLewLJQyFXEpOp2h+mfN2bPrzYaOFNCJjO4Js9deKbRHTOSaiP2FRwZqDLdQwy2+SEGeXPZ94yYw==", + "version": "4.1.2", + "resolved": "https://registry.npmjs.org/@chromatic-com/storybook/-/storybook-4.1.2.tgz", + "integrity": "sha512-QAWGtHwib0qsP5CcO64aJCF75zpFgpKK3jNpxILzQiPK3sVo4EmnVGJVdwcZWpWrGdH8E4YkncGoitw4EXzKMg==", "dev": true, "license": "MIT", "dependencies": { @@ -150,7 +150,7 @@ "yarn": ">=1.22.18" }, "peerDependencies": { - "storybook": "^0.0.0-0 || ^9.0.0 || ^9.1.0-0" + "storybook": "^0.0.0-0 || ^9.0.0 || ^9.1.0-0 || ^9.2.0-0 || ^10.0.0-0 || ^10.1.0-0 || ^10.2.0-0 || ^10.3.0-0" } }, "node_modules/@esbuild/aix-ppc64": { @@ -894,6 +894,17 @@ "@jridgewell/trace-mapping": "^0.3.24" } }, + "node_modules/@jridgewell/remapping": { + "version": "2.3.5", + "resolved": "https://registry.npmjs.org/@jridgewell/remapping/-/remapping-2.3.5.tgz", + "integrity": "sha512-LI9u/+laYG4Ds1TDKSJW2YPrIlcVYOwi2fUC6xB43lueCjgxV4lffOCZCtYFiH6TNOX+tQKXx97T4IKHbhyHEQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jridgewell/gen-mapping": "^0.3.5", + "@jridgewell/trace-mapping": "^0.3.24" + } + }, "node_modules/@jridgewell/resolve-uri": { "version": "3.1.2", "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz", @@ -1502,13 +1513,13 @@ } }, "node_modules/@playwright/test": { - "version": "1.54.1", - "resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.54.1.tgz", - "integrity": "sha512-FS8hQ12acieG2dYSksmLOF7BNxnVf2afRJdCuM1eMSxj6QTSE6G4InGF7oApGgDb65MX7AwMVlIkpru0yZA4Xw==", + "version": "1.56.1", + "resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.56.1.tgz", + "integrity": "sha512-vSMYtL/zOcFpvJCW71Q/OEGQb7KYBPAdKh35WNSkaZA75JlAO8ED8UN6GUNTm3drWomcbcqRPFqQbLae8yBTdg==", "dev": true, "license": "Apache-2.0", "dependencies": { - "playwright": "1.54.1" + "playwright": "1.56.1" }, "bin": { "playwright": "cli.js" @@ -1812,9 +1823,9 @@ "license": "MIT" }, "node_modules/@storybook/addon-a11y": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/addon-a11y/-/addon-a11y-9.0.17.tgz", - "integrity": "sha512-9cXNK3q/atx3hwJAt9HkJbd9vUxCXfKKiNNuSACbf8h9/j6u3jktulKOf6Xjc3B8lwn6ZpdK/x1HHZN2kTqsvg==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/addon-a11y/-/addon-a11y-10.0.7.tgz", + "integrity": "sha512-JsYPpZ/n67/2bI1XJeyrAWHHQkHemPkPHjCA0tAUnMz1Shlo/LV2q1Ahgpxoihx4strbHwZz71bcS4MqkHBduA==", "dev": true, "license": "MIT", "dependencies": { @@ -1826,20 +1837,20 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^9.0.17" + "storybook": "^10.0.7" } }, "node_modules/@storybook/addon-docs": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/addon-docs/-/addon-docs-9.0.17.tgz", - "integrity": "sha512-LOX/kKgQGnyulrqZHsvf77+ZoH/nSUaplGr5hvZglW/U6ak6fO9seJyXAzVKEnC6p+F8n02kFBZbi3s+znQhSg==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/addon-docs/-/addon-docs-10.0.7.tgz", + "integrity": "sha512-qQQMoeYZC4W+/8ubfOZiTrE8nYC/f4wWP1uq4peRyDy1N2nIN9SwhyxwMn0m3VpeGmRBga5dLvJY9ko6SnJekg==", "dev": true, "license": "MIT", "dependencies": { "@mdx-js/react": "^3.0.0", - "@storybook/csf-plugin": "9.0.17", - "@storybook/icons": "^1.2.12", - "@storybook/react-dom-shim": "9.0.17", + "@storybook/csf-plugin": "10.0.7", + "@storybook/icons": "^1.6.0", + "@storybook/react-dom-shim": "10.0.7", "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "ts-dedent": "^2.0.0" @@ -1849,13 +1860,13 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^9.0.17" + "storybook": "^10.0.7" } }, "node_modules/@storybook/addon-svelte-csf": { - "version": "5.0.7", - "resolved": "https://registry.npmjs.org/@storybook/addon-svelte-csf/-/addon-svelte-csf-5.0.7.tgz", - "integrity": "sha512-6Zmy5HjOlrrG6OoKRTGDr9LR6zRK4/Sa7raFzQRKHGASgMlfKsMdNTNO0sxnMUWCu2JMS6HsuoLtB3Ma8SlYtg==", + "version": "5.0.10", + "resolved": "https://registry.npmjs.org/@storybook/addon-svelte-csf/-/addon-svelte-csf-5.0.10.tgz", + "integrity": "sha512-poSvTS7VdaQ42ZoqW5e4+2Hv1iLO0mekH9fwn/QuBNse48R4WlTyR8XFbHRTfatl9gdc9ZYC4uWzazrmV6zGIA==", "dev": true, "license": "MIT", "dependencies": { @@ -1868,22 +1879,22 @@ "zimmerframe": "^1.1.2" }, "peerDependencies": { - "@storybook/svelte": "^0.0.0-0 || ^8.2.0 || ^9.0.0 || ^9.1.0-0", + "@storybook/svelte": "^0.0.0-0 || ^8.2.0 || ^9.0.0 || ^9.1.0-0 || ^10.0.0-0", "@sveltejs/vite-plugin-svelte": "^4.0.0 || ^5.0.0 || ^6.0.0", - "storybook": "^0.0.0-0 || ^8.2.0 || ^9.0.0 || ^9.1.0-0", + "storybook": "^0.0.0-0 || ^8.2.0 || ^9.0.0 || ^9.1.0-0 || ^10.0.0-0", "svelte": "^5.0.0", "vite": "^5.0.0 || ^6.0.0 || ^7.0.0" } }, "node_modules/@storybook/addon-vitest": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/addon-vitest/-/addon-vitest-9.0.17.tgz", - "integrity": "sha512-eogqcGbACR1sTedBSE2SP/4QV1ruicHYEhYjBtoPIjvYgymN1g5KSuQNysLx4f0SvAzczrcNjX2WVVLX2DVyzA==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/addon-vitest/-/addon-vitest-10.0.7.tgz", + "integrity": "sha512-i6v/mAl+elrUxb+1f4NdnM17t/fg+KGJWL1U9quflXTd3KiLY0xJB4LwNP6yYo7Imc5NIO2fRkJbGvNqLBRe2Q==", "dev": true, "license": "MIT", "dependencies": { "@storybook/global": "^5.0.0", - "@storybook/icons": "^1.4.0", + "@storybook/icons": "^1.6.0", "prompts": "^2.4.0", "ts-dedent": "^2.2.0" }, @@ -1892,15 +1903,19 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "@vitest/browser": "^3.0.0", - "@vitest/runner": "^3.0.0", - "storybook": "^9.0.17", - "vitest": "^3.0.0" + "@vitest/browser": "^3.0.0 || ^4.0.0", + "@vitest/browser-playwright": "^4.0.0", + "@vitest/runner": "^3.0.0 || ^4.0.0", + "storybook": "^10.0.7", + "vitest": "^3.0.0 || ^4.0.0" }, "peerDependenciesMeta": { "@vitest/browser": { "optional": true }, + "@vitest/browser-playwright": { + "optional": true + }, "@vitest/runner": { "optional": true }, @@ -1910,13 +1925,13 @@ } }, "node_modules/@storybook/builder-vite": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/builder-vite/-/builder-vite-9.0.17.tgz", - "integrity": "sha512-lyuvgGhb0NaVk1tdB4xwzky6+YXQfxlxfNQqENYZ9uYQZdPfErMa4ZTXVQTV+CQHAa2NL+p/dG2JPAeu39e9UA==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/builder-vite/-/builder-vite-10.0.7.tgz", + "integrity": "sha512-wk2TAoUY5+9t78GWVBndu9rEo9lo6Ec3SRrLT4VpIlcS2GPK+5f26UC2uvIBwOF/N7JrUUKq/zWDZ3m+do9QDg==", "dev": true, "license": "MIT", "dependencies": { - "@storybook/csf-plugin": "9.0.17", + "@storybook/csf-plugin": "10.0.7", "ts-dedent": "^2.0.0" }, "funding": { @@ -1924,7 +1939,7 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^9.0.17", + "storybook": "^10.0.7", "vite": "^5.0.0 || ^6.0.0 || ^7.0.0" } }, @@ -1939,20 +1954,38 @@ } }, "node_modules/@storybook/csf-plugin": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/csf-plugin/-/csf-plugin-9.0.17.tgz", - "integrity": "sha512-6Q4eo1ObrLlsnB6bIt6T8+45XAb4to2pQGNrI7QPkLQRLrZinrJcNbLY7AGkyIoCOEsEbq08n09/nClQUbu8HA==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/csf-plugin/-/csf-plugin-10.0.7.tgz", + "integrity": "sha512-YaYYlCyJBwxaMk7yREOdz+9MDSgxIYGdeJ9EIq/bUndmkoj9SRo1P9/0lC5dseWQoiGy4T3PbZiWruD8uM5m3g==", "dev": true, "license": "MIT", "dependencies": { - "unplugin": "^1.3.1" + "unplugin": "^2.3.5" }, "funding": { "type": "opencollective", "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^9.0.17" + "esbuild": "*", + "rollup": "*", + "storybook": "^10.0.7", + "vite": "*", + "webpack": "*" + }, + "peerDependenciesMeta": { + "esbuild": { + "optional": true + }, + "rollup": { + "optional": true + }, + "vite": { + "optional": true + }, + "webpack": { + "optional": true + } } }, "node_modules/@storybook/global": { @@ -1963,9 +1996,9 @@ "license": "MIT" }, "node_modules/@storybook/icons": { - "version": "1.4.0", - "resolved": "https://registry.npmjs.org/@storybook/icons/-/icons-1.4.0.tgz", - "integrity": "sha512-Td73IeJxOyalzvjQL+JXx72jlIYHgs+REaHiREOqfpo3A2AYYG71AUbcv+lg7mEDIweKVCxsMQ0UKo634c8XeA==", + "version": "1.6.0", + "resolved": "https://registry.npmjs.org/@storybook/icons/-/icons-1.6.0.tgz", + "integrity": "sha512-hcFZIjW8yQz8O8//2WTIXylm5Xsgc+lW9ISLgUk1xGmptIJQRdlhVIXCpSyLrQaaRiyhQRaVg7l3BD9S216BHw==", "dev": true, "license": "MIT", "engines": { @@ -1977,9 +2010,9 @@ } }, "node_modules/@storybook/react-dom-shim": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/react-dom-shim/-/react-dom-shim-9.0.17.tgz", - "integrity": "sha512-ak/x/m6MDDxdE6rCDymTltaiQF3oiKrPHSwfM+YPgQR6MVmzTTs4+qaPfeev7FZEHq23IkfDMTmSTTJtX7Vs9A==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/react-dom-shim/-/react-dom-shim-10.0.7.tgz", + "integrity": "sha512-bp4OnMtZGwPJQDqNRi4K5iibLbZ2TZZMkWW7oSw5jjPFpGSreSjCe8LH9yj/lDnK8Ox9bGMCBFE5RV5XuML29w==", "dev": true, "license": "MIT", "funding": { @@ -1987,126 +2020,75 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0-beta", - "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0-beta", - "storybook": "^9.0.17" + "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", + "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", + "storybook": "^10.0.7" } }, "node_modules/@storybook/svelte": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/svelte/-/svelte-9.0.17.tgz", - "integrity": "sha512-RwOswdq7S3+ZOuoM/oRrcmlsKdjcd/3wMHbuirzYoAhdwsjubSuRepMV64O9RnlXd3x7rZw4fXpq1M/SVo5XiQ==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/svelte/-/svelte-10.0.7.tgz", + "integrity": "sha512-rO+YQhHucy47Vh67z318pALmd6x+K1Kj30Fb4a6oOEw4xn4zCo9KTmkMWs24c4oduEXD/eJu3badlRmsVXzyfA==", "dev": true, "license": "MIT", "dependencies": { "ts-dedent": "^2.0.0", "type-fest": "~2.19" }, - "engines": { - "node": ">=20.0.0" - }, "funding": { "type": "opencollective", "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^9.0.17", + "storybook": "^10.0.7", "svelte": "^5.0.0" } }, - "node_modules/@storybook/sveltekit": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/sveltekit/-/sveltekit-9.0.17.tgz", - "integrity": "sha512-CUOATuW5Qk3SjNvmjH+wyx2GCsMF1cvw3gwkujV9kehPebzV20NhgHpbzSoepvwF7+Bj6jl8V6UxiMWk0jJFmA==", + "node_modules/@storybook/svelte-vite": { + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/svelte-vite/-/svelte-vite-10.0.7.tgz", + "integrity": "sha512-q9/RtrhX1CnznO6AO9MDEy1bsccbGeRxW28FLpgUrztV4IGZ/dFUrFIFurKRyuA3/nFsbtzp1F5jFt3RExmmTw==", "dev": true, "license": "MIT", "dependencies": { - "@storybook/builder-vite": "9.0.17", - "@storybook/svelte": "9.0.17", - "@storybook/svelte-vite": "9.0.17" - }, - "engines": { - "node": ">=20.0.0" + "@storybook/builder-vite": "10.0.7", + "@storybook/svelte": "10.0.7", + "magic-string": "^0.30.0", + "svelte2tsx": "^0.7.44", + "typescript": "^4.9.4 || ^5.0.0" }, "funding": { "type": "opencollective", "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^9.0.17", + "@sveltejs/vite-plugin-svelte": "^2.0.0 || ^3.0.0 || ^4.0.0 || ^5.0.0 || ^6.0.0", + "storybook": "^10.0.7", "svelte": "^5.0.0", "vite": "^5.0.0 || ^6.0.0 || ^7.0.0" } }, - "node_modules/@storybook/sveltekit/node_modules/@storybook/svelte-vite": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/@storybook/svelte-vite/-/svelte-vite-9.0.17.tgz", - "integrity": "sha512-fRIxOZy9IRI6BfL1LgFn+B+IckGOlT1SstD01y9ddO4pVKWih/l+vb44bnZs+Z0faJZbrG/LgfnXTOPj052Z8g==", + "node_modules/@storybook/sveltekit": { + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/@storybook/sveltekit/-/sveltekit-10.0.7.tgz", + "integrity": "sha512-ujTW7PfWvgBrzd7jzaZe9JgjUeM5YvBKm+xru6t7Dr4bdfmkKqlZHPRdXn/sy+fQNyfg6JL2WKy2KIIeA+RvSg==", "dev": true, "license": "MIT", "dependencies": { - "@storybook/builder-vite": "9.0.17", - "@storybook/svelte": "9.0.17", - "magic-string": "^0.30.0", - "svelte2tsx": "^0.7.35", - "typescript": "^4.9.4 || ^5.0.0" - }, - "engines": { - "node": ">=20.0.0" + "@storybook/builder-vite": "10.0.7", + "@storybook/svelte": "10.0.7", + "@storybook/svelte-vite": "10.0.7" }, "funding": { "type": "opencollective", "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "@sveltejs/vite-plugin-svelte": "^2.0.0 || ^3.0.0 || ^4.0.0 || ^5.0.0", - "storybook": "^9.0.17", + "storybook": "^10.0.7", "svelte": "^5.0.0", "vite": "^5.0.0 || ^6.0.0 || ^7.0.0" } }, - "node_modules/@storybook/sveltekit/node_modules/@sveltejs/vite-plugin-svelte": { - "version": "5.1.1", - "resolved": "https://registry.npmjs.org/@sveltejs/vite-plugin-svelte/-/vite-plugin-svelte-5.1.1.tgz", - "integrity": "sha512-Y1Cs7hhTc+a5E9Va/xwKlAJoariQyHY+5zBgCZg4PFWNYQ1nMN9sjK1zhw1gK69DuqVP++sht/1GZg1aRwmAXQ==", - "dev": true, - "license": "MIT", - "peer": true, - "dependencies": { - "@sveltejs/vite-plugin-svelte-inspector": "^4.0.1", - "debug": "^4.4.1", - "deepmerge": "^4.3.1", - "kleur": "^4.1.5", - "magic-string": "^0.30.17", - "vitefu": "^1.0.6" - }, - "engines": { - "node": "^18.0.0 || ^20.0.0 || >=22" - }, - "peerDependencies": { - "svelte": "^5.0.0", - "vite": "^6.0.0" - } - }, - "node_modules/@storybook/sveltekit/node_modules/@sveltejs/vite-plugin-svelte/node_modules/@sveltejs/vite-plugin-svelte-inspector": { - "version": "4.0.1", - "resolved": "https://registry.npmjs.org/@sveltejs/vite-plugin-svelte-inspector/-/vite-plugin-svelte-inspector-4.0.1.tgz", - "integrity": "sha512-J/Nmb2Q2y7mck2hyCX4ckVHcR5tu2J+MtBEQqpDrrgELZ2uvraQcK/ioCV61AqkdXFgriksOKIceDcQmqnGhVw==", - "dev": true, - "license": "MIT", - "peer": true, - "dependencies": { - "debug": "^4.3.7" - }, - "engines": { - "node": "^18.0.0 || ^20.0.0 || >=22" - }, - "peerDependencies": { - "@sveltejs/vite-plugin-svelte": "^5.0.0", - "svelte": "^5.0.0", - "vite": "^6.0.0" - } - }, "node_modules/@sveltejs/acorn-typescript": { "version": "1.0.5", "resolved": "https://registry.npmjs.org/@sveltejs/acorn-typescript/-/acorn-typescript-1.0.5.tgz", @@ -2117,9 +2099,9 @@ } }, "node_modules/@sveltejs/adapter-static": { - "version": "3.0.9", - "resolved": "https://registry.npmjs.org/@sveltejs/adapter-static/-/adapter-static-3.0.9.tgz", - "integrity": "sha512-aytHXcMi7lb9ljsWUzXYQ0p5X1z9oWud2olu/EpmH7aCu4m84h7QLvb5Wp+CFirKcwoNnYvYWhyP/L8Vh1ztdw==", + "version": "3.0.10", + "resolved": "https://registry.npmjs.org/@sveltejs/adapter-static/-/adapter-static-3.0.10.tgz", + "integrity": "sha512-7D9lYFWJmB7zxZyTE/qxjksvMqzMuYrrsyh1f4AlZqeZeACPRySjbC3aFiY55wb1tWUaKOQG9PVbm74JcN2Iew==", "dev": true, "license": "MIT", "peerDependencies": { @@ -2127,9 +2109,9 @@ } }, "node_modules/@sveltejs/kit": { - "version": "2.37.0", - "resolved": "https://registry.npmjs.org/@sveltejs/kit/-/kit-2.37.0.tgz", - "integrity": "sha512-xgKtpjQ6Ry4mdShd01ht5AODUsW7+K1iValPDq7QX8zI1hWOKREH9GjG8SRCN5tC4K7UXmMhuQam7gbLByVcnw==", + "version": "2.48.4", + "resolved": "https://registry.npmjs.org/@sveltejs/kit/-/kit-2.48.4.tgz", + "integrity": "sha512-TGFX1pZUt9qqY20Cv5NyYvy0iLWHf2jXi8s+eCGsig7jQMdwZWKUFMR6TbvFNhfDSUpc1sH/Y5EHv20g3HHA3g==", "dev": true, "license": "MIT", "dependencies": { @@ -2166,16 +2148,15 @@ } }, "node_modules/@sveltejs/vite-plugin-svelte": { - "version": "6.1.0", - "resolved": "https://registry.npmjs.org/@sveltejs/vite-plugin-svelte/-/vite-plugin-svelte-6.1.0.tgz", - "integrity": "sha512-+U6lz1wvGEG/BvQyL4z/flyNdQ9xDNv5vrh+vWBWTHaebqT0c9RNggpZTo/XSPoHsSCWBlYaTlRX8pZ9GATXCw==", + "version": "6.2.1", + "resolved": "https://registry.npmjs.org/@sveltejs/vite-plugin-svelte/-/vite-plugin-svelte-6.2.1.tgz", + "integrity": "sha512-YZs/OSKOQAQCnJvM/P+F1URotNnYNeU3P2s4oIpzm1uFaqUEqRxUB0g5ejMjEb5Gjb9/PiBI5Ktrq4rUUF8UVQ==", "dev": true, "license": "MIT", "dependencies": { - "@sveltejs/vite-plugin-svelte-inspector": "^5.0.0-next.1", + "@sveltejs/vite-plugin-svelte-inspector": "^5.0.0", "debug": "^4.4.1", "deepmerge": "^4.3.1", - "kleur": "^4.1.5", "magic-string": "^0.30.17", "vitefu": "^1.1.1" }, @@ -3361,19 +3342,6 @@ "node": ">= 0.8" } }, - "node_modules/better-opn": { - "version": "3.0.2", - "resolved": "https://registry.npmjs.org/better-opn/-/better-opn-3.0.2.tgz", - "integrity": "sha512-aVNobHnJqLiUelTaHat9DZ1qM2w0C0Eym4LPI/3JxOnSokGVdsl1T1kN7TFvsEAD8G47A6VKQ0TVHqbBnYMJlQ==", - "dev": true, - "license": "MIT", - "dependencies": { - "open": "^8.0.4" - }, - "engines": { - "node": ">=12.0.0" - } - }, "node_modules/bits-ui": { "version": "2.8.11", "resolved": "https://registry.npmjs.org/bits-ui/-/bits-ui-2.8.11.tgz", @@ -3844,16 +3812,6 @@ "node": ">=0.10.0" } }, - "node_modules/define-lazy-prop": { - "version": "2.0.0", - "resolved": "https://registry.npmjs.org/define-lazy-prop/-/define-lazy-prop-2.0.0.tgz", - "integrity": "sha512-Ds09qNh8yw3khSjiJjiUInaGX9xlqZDY7JVryGxdxV7NPeuqQfplOpQ66yJFZut3jLa5zOwkXw1g9EI2uKh4Og==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=8" - } - }, "node_modules/dequal": { "version": "2.0.3", "resolved": "https://registry.npmjs.org/dequal/-/dequal-2.0.3.tgz", @@ -4042,19 +4000,6 @@ "@esbuild/win32-x64": "0.25.8" } }, - "node_modules/esbuild-register": { - "version": "3.6.0", - "resolved": "https://registry.npmjs.org/esbuild-register/-/esbuild-register-3.6.0.tgz", - "integrity": "sha512-H2/S7Pm8a9CL1uhp9OvjwrBh5Pvx0H8qVOxNu8Wed9Y7qv56MPtq+GGM8RJpq6glYJn9Wspr8uw7l55uyinNeg==", - "dev": true, - "license": "MIT", - "dependencies": { - "debug": "^4.3.4" - }, - "peerDependencies": { - "esbuild": ">=0.12 <1" - } - }, "node_modules/escape-string-regexp": { "version": "4.0.0", "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-4.0.0.tgz", @@ -4146,20 +4091,17 @@ } }, "node_modules/eslint-plugin-storybook": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/eslint-plugin-storybook/-/eslint-plugin-storybook-9.0.17.tgz", - "integrity": "sha512-IuTdlwCEwoDNobdygRCxNhlKXHmsDfPtPvHGcsY35x2Bx8KItrjfekO19gJrjc1VT2CMfcZMYF8OBKaxHELupw==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/eslint-plugin-storybook/-/eslint-plugin-storybook-10.0.7.tgz", + "integrity": "sha512-qOQq9KdT1jsBgT3qsxUH2n67aj1WR8D1XCoER8Q6yuVlS5TimNwk1mZeWkXVf/o4RQQT6flT2y5cG2gPLZPvJA==", "dev": true, "license": "MIT", "dependencies": { "@typescript-eslint/utils": "^8.8.1" }, - "engines": { - "node": ">=20.0.0" - }, "peerDependencies": { "eslint": ">=8", - "storybook": "^9.0.17" + "storybook": "^10.0.7" } }, "node_modules/eslint-plugin-svelte": { @@ -4405,11 +4347,14 @@ } }, "node_modules/fdir": { - "version": "6.4.6", - "resolved": "https://registry.npmjs.org/fdir/-/fdir-6.4.6.tgz", - "integrity": "sha512-hiFoqpyZcfNm1yc4u8oWCf9A2c4D3QjCrks3zmoVKVxpQRzmPNar1hUJcBG2RQHvEVGDN+Jm81ZheVLAQMK6+w==", + "version": "6.5.0", + "resolved": "https://registry.npmjs.org/fdir/-/fdir-6.5.0.tgz", + "integrity": "sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==", "dev": true, "license": "MIT", + "engines": { + "node": ">=12.0.0" + }, "peerDependencies": { "picomatch": "^3 || ^4" }, @@ -5072,22 +5017,6 @@ "integrity": "sha512-0aO8FkhNZlj/ZIbNi7Lxxr12obT7cL1moPfE4tg1LkX7LlLfC6DeX4l2ZEud1ukP9jNQyNnfzQVqwbwmAATY4Q==", "license": "MIT" }, - "node_modules/is-docker": { - "version": "2.2.1", - "resolved": "https://registry.npmjs.org/is-docker/-/is-docker-2.2.1.tgz", - "integrity": "sha512-F+i2BKsFrH66iaUFc0woD8sLy8getkwTwtOBjvs56Cx4CgJDeKQeqfz8wAYiSb8JOprWhHH5p77PbmYCvvUuXQ==", - "dev": true, - "license": "MIT", - "bin": { - "is-docker": "cli.js" - }, - "engines": { - "node": ">=8" - }, - "funding": { - "url": "https://github.com/sponsors/sindresorhus" - } - }, "node_modules/is-extglob": { "version": "2.1.1", "resolved": "https://registry.npmjs.org/is-extglob/-/is-extglob-2.1.1.tgz", @@ -5133,19 +5062,6 @@ "url": "https://github.com/sponsors/sindresorhus" } }, - "node_modules/is-wsl": { - "version": "2.2.0", - "resolved": "https://registry.npmjs.org/is-wsl/-/is-wsl-2.2.0.tgz", - "integrity": "sha512-fKzAra0rGJUUBwGBgNkHZuToZcn+TtXHpeCgmkMJMMYx1sQDYaCSyjJBSCa2nH1DGm7s3n1oBnohoVTBaN7Lww==", - "dev": true, - "license": "MIT", - "dependencies": { - "is-docker": "^2.0.0" - }, - "engines": { - "node": ">=8" - } - }, "node_modules/isexe": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz", @@ -5591,16 +5507,6 @@ "dev": true, "license": "MIT" }, - "node_modules/lower-case": { - "version": "2.0.2", - "resolved": "https://registry.npmjs.org/lower-case/-/lower-case-2.0.2.tgz", - "integrity": "sha512-7fm3l3NAF9WfN6W3JOmf5drwpVqX78JtoGJ3A6W0a6ZnldM41w2fV5D490psKFTpMds8TJse/eHLFFsNHHjHgg==", - "dev": true, - "license": "MIT", - "dependencies": { - "tslib": "^2.0.3" - } - }, "node_modules/lowlight": { "version": "3.3.0", "resolved": "https://registry.npmjs.org/lowlight/-/lowlight-3.3.0.tgz", @@ -6783,17 +6689,6 @@ "dev": true, "license": "MIT" }, - "node_modules/no-case": { - "version": "3.0.4", - "resolved": "https://registry.npmjs.org/no-case/-/no-case-3.0.4.tgz", - "integrity": "sha512-fgAN3jGAh+RoxUGZHTSOLJIqUc2wmoBwGR4tbpNAKmmovFoWq0OdRkb0VkldReO2a2iBT/OEulG9XSUc10r3zg==", - "dev": true, - "license": "MIT", - "dependencies": { - "lower-case": "^2.0.2", - "tslib": "^2.0.3" - } - }, "node_modules/node-addon-api": { "version": "7.1.1", "resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-7.1.1.tgz", @@ -6815,24 +6710,6 @@ "url": "https://github.com/sponsors/ljharb" } }, - "node_modules/open": { - "version": "8.4.2", - "resolved": "https://registry.npmjs.org/open/-/open-8.4.2.tgz", - "integrity": "sha512-7x81NCL719oNbsq/3mh+hVrAWmFuEYUqrq/Iw3kUzH8ReypT9QQ0BLoJS7/G9k6N81XjW4qHWtjWwe/9eLy1EQ==", - "dev": true, - "license": "MIT", - "dependencies": { - "define-lazy-prop": "^2.0.0", - "is-docker": "^2.1.1", - "is-wsl": "^2.2.0" - }, - "engines": { - "node": ">=12" - }, - "funding": { - "url": "https://github.com/sponsors/sindresorhus" - } - }, "node_modules/opener": { "version": "1.5.2", "resolved": "https://registry.npmjs.org/opener/-/opener-1.5.2.tgz", @@ -6919,17 +6796,6 @@ "url": "https://github.com/inikulin/parse5?sponsor=1" } }, - "node_modules/pascal-case": { - "version": "3.1.2", - "resolved": "https://registry.npmjs.org/pascal-case/-/pascal-case-3.1.2.tgz", - "integrity": "sha512-uWlGT3YSnK9x3BQJaOdcZwrnV6hPpd8jFH1/ucpiLRPh/2zCVJKS19E4GvYHvaCcACn3foXZ0cLB9Wrx1KGe5g==", - "dev": true, - "license": "MIT", - "dependencies": { - "no-case": "^3.0.4", - "tslib": "^2.0.3" - } - }, "node_modules/path-exists": { "version": "4.0.0", "resolved": "https://registry.npmjs.org/path-exists/-/path-exists-4.0.0.tgz", @@ -7000,13 +6866,13 @@ } }, "node_modules/playwright": { - "version": "1.54.1", - "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.54.1.tgz", - "integrity": "sha512-peWpSwIBmSLi6aW2auvrUtf2DqY16YYcCMO8rTVx486jKmDTJg7UAhyrraP98GB8BoPURZP8+nxO7TSd4cPr5g==", + "version": "1.56.1", + "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.56.1.tgz", + "integrity": "sha512-aFi5B0WovBHTEvpM3DzXTUaeN6eN0qWnTkKx4NQaH4Wvcmc153PdaY2UBdSYKaGYw+UyWXSVyxDUg5DoPEttjw==", "dev": true, "license": "Apache-2.0", "dependencies": { - "playwright-core": "1.54.1" + "playwright-core": "1.56.1" }, "bin": { "playwright": "cli.js" @@ -7019,9 +6885,9 @@ } }, "node_modules/playwright-core": { - "version": "1.54.1", - "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.54.1.tgz", - "integrity": "sha512-Nbjs2zjj0htNhzgiy5wu+3w09YetDx5pkrpI/kZotDlDUaYk0HVA5xrBVPdow4SAUIlhgKcJeJg4GRKW6xHusA==", + "version": "1.56.1", + "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.56.1.tgz", + "integrity": "sha512-hutraynyn31F+Bifme+Ps9Vq59hKuUCz7H1kDOcBs+2oGguKkWTU50bBWrtz34OUWmIwpBTWDxaRPXrIXkgvmQ==", "dev": true, "license": "Apache-2.0", "bin": { @@ -7852,6 +7718,13 @@ "dev": true, "license": "MIT" }, + "node_modules/scule": { + "version": "1.3.0", + "resolved": "https://registry.npmjs.org/scule/-/scule-1.3.0.tgz", + "integrity": "sha512-6FtHJEvt+pVMIB9IBY+IcCJ6Z5f1iQnytgyfKMhDKgmzYG+TeH/wx1y3l27rshSbLiSanrR9ffZDrEsmjlQF2g==", + "dev": true, + "license": "MIT" + }, "node_modules/secure-compare": { "version": "3.0.1", "resolved": "https://registry.npmjs.org/secure-compare/-/secure-compare-3.0.1.tgz", @@ -8052,26 +7925,26 @@ "license": "MIT" }, "node_modules/storybook": { - "version": "9.0.17", - "resolved": "https://registry.npmjs.org/storybook/-/storybook-9.0.17.tgz", - "integrity": "sha512-O+9jgJ+Trlq9VGD1uY4OBLKQWHHDKM/A/pA8vMW6PVehhGHNvpzcIC1bngr6mL5gGHZP2nBv+9XG8pTMcggMmg==", + "version": "10.0.7", + "resolved": "https://registry.npmjs.org/storybook/-/storybook-10.0.7.tgz", + "integrity": "sha512-7smAu0o+kdm378Q2uIddk32pn0UdIbrtTVU+rXRVtTVTCrK/P2cCui2y4JH+Bl3NgEq1bbBQpCAF/HKrDjk2Qw==", "dev": true, "license": "MIT", "dependencies": { "@storybook/global": "^5.0.0", + "@storybook/icons": "^1.6.0", "@testing-library/jest-dom": "^6.6.3", "@testing-library/user-event": "^14.6.1", "@vitest/expect": "3.2.4", + "@vitest/mocker": "3.2.4", "@vitest/spy": "3.2.4", - "better-opn": "^3.0.2", "esbuild": "^0.18.0 || ^0.19.0 || ^0.20.0 || ^0.21.0 || ^0.22.0 || ^0.23.0 || ^0.24.0 || ^0.25.0", - "esbuild-register": "^3.5.0", "recast": "^0.23.5", "semver": "^7.6.2", "ws": "^8.18.0" }, "bin": { - "storybook": "bin/index.cjs" + "storybook": "dist/bin/dispatcher.js" }, "funding": { "type": "opencollective", @@ -8418,14 +8291,14 @@ } }, "node_modules/svelte2tsx": { - "version": "0.7.41", - "resolved": "https://registry.npmjs.org/svelte2tsx/-/svelte2tsx-0.7.41.tgz", - "integrity": "sha512-/TUwpyn/Qc1wcGuayf2GSwvZ7htdAOzpo0JFFm96srKnRXoTD0gy4n06g+XgH8w016S3lPtyFVtFAm+0yJ0BZw==", + "version": "0.7.45", + "resolved": "https://registry.npmjs.org/svelte2tsx/-/svelte2tsx-0.7.45.tgz", + "integrity": "sha512-cSci+mYGygYBHIZLHlm/jYlEc1acjAHqaQaDFHdEBpUueM9kSTnPpvPtSl5VkJOU1qSJ7h1K+6F/LIUYiqC8VA==", "dev": true, "license": "MIT", "dependencies": { "dedent-js": "^1.0.1", - "pascal-case": "^3.1.1" + "scule": "^1.3.0" }, "peerDependencies": { "svelte": "^3.55 || ^4.0.0-next.0 || ^4.0 || ^5.0.0-next.0", @@ -8535,14 +8408,14 @@ "license": "MIT" }, "node_modules/tinyglobby": { - "version": "0.2.14", - "resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.14.tgz", - "integrity": "sha512-tX5e7OM1HnYr2+a2C/4V0htOcSQcoSTH9KgJnVvNm5zm/cyEWKJ7j7YutsH9CxMdtOkkLFy2AHrMci9IM8IPZQ==", + "version": "0.2.15", + "resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.15.tgz", + "integrity": "sha512-j2Zq4NyQYG5XMST4cbs02Ak8iJUdxRM0XI5QyxXuZOzKOINmWurp3smXu3y5wDcJrptwpSjgXHzIQxR0omXljQ==", "dev": true, "license": "MIT", "dependencies": { - "fdir": "^6.4.4", - "picomatch": "^4.0.2" + "fdir": "^6.5.0", + "picomatch": "^4.0.3" }, "engines": { "node": ">=12.0.0" @@ -8918,17 +8791,19 @@ } }, "node_modules/unplugin": { - "version": "1.16.1", - "resolved": "https://registry.npmjs.org/unplugin/-/unplugin-1.16.1.tgz", - "integrity": "sha512-4/u/j4FrCKdi17jaxuJA0jClGxB1AvU2hw/IuayPc4ay1XGaJs/rbb4v5WKwAjNifjmXK9PIFyuPiaK8azyR9w==", + "version": "2.3.10", + "resolved": "https://registry.npmjs.org/unplugin/-/unplugin-2.3.10.tgz", + "integrity": "sha512-6NCPkv1ClwH+/BGE9QeoTIl09nuiAt0gS28nn1PvYXsGKRwM2TCbFA2QiilmehPDTXIe684k4rZI1yl3A1PCUw==", "dev": true, "license": "MIT", "dependencies": { - "acorn": "^8.14.0", + "@jridgewell/remapping": "^2.3.5", + "acorn": "^8.15.0", + "picomatch": "^4.0.3", "webpack-virtual-modules": "^0.6.2" }, "engines": { - "node": ">=14.0.0" + "node": ">=18.12.0" } }, "node_modules/uri-js": { @@ -9054,18 +8929,18 @@ } }, "node_modules/vite": { - "version": "7.0.5", - "resolved": "https://registry.npmjs.org/vite/-/vite-7.0.5.tgz", - "integrity": "sha512-1mncVwJxy2C9ThLwz0+2GKZyEXuC3MyWtAAlNftlZZXZDP3AJt5FmwcMit/IGGaNZ8ZOB2BNO/HFUB+CpN0NQw==", + "version": "7.2.2", + "resolved": "https://registry.npmjs.org/vite/-/vite-7.2.2.tgz", + "integrity": "sha512-BxAKBWmIbrDgrokdGZH1IgkIk/5mMHDreLDmCJ0qpyJaAteP8NvMhkwr/ZCQNqNH97bw/dANTE9PDzqwJghfMQ==", "dev": true, "license": "MIT", "dependencies": { "esbuild": "^0.25.0", - "fdir": "^6.4.6", - "picomatch": "^4.0.2", + "fdir": "^6.5.0", + "picomatch": "^4.0.3", "postcss": "^8.5.6", - "rollup": "^4.40.0", - "tinyglobby": "^0.2.14" + "rollup": "^4.43.0", + "tinyglobby": "^0.2.15" }, "bin": { "vite": "bin/vite.js" diff --git a/tools/server/webui/package.json b/tools/server/webui/package.json index 92c7457bd3..8b88f691a4 100644 --- a/tools/server/webui/package.json +++ b/tools/server/webui/package.json @@ -24,20 +24,20 @@ "cleanup": "rm -rf .svelte-kit build node_modules test-results" }, "devDependencies": { - "@chromatic-com/storybook": "^4.0.1", + "@chromatic-com/storybook": "^4.1.2", "@eslint/compat": "^1.2.5", "@eslint/js": "^9.18.0", "@internationalized/date": "^3.8.2", "@lucide/svelte": "^0.515.0", "@playwright/test": "^1.49.1", - "@storybook/addon-a11y": "^9.0.17", - "@storybook/addon-docs": "^9.0.17", - "@storybook/addon-svelte-csf": "^5.0.7", - "@storybook/addon-vitest": "^9.0.17", - "@storybook/sveltekit": "^9.0.17", - "@sveltejs/adapter-static": "^3.0.8", - "@sveltejs/kit": "^2.22.0", - "@sveltejs/vite-plugin-svelte": "^6.0.0", + "@storybook/addon-a11y": "^10.0.7", + "@storybook/addon-docs": "^10.0.7", + "@storybook/addon-svelte-csf": "^5.0.10", + "@storybook/addon-vitest": "^10.0.7", + "@storybook/sveltekit": "^10.0.7", + "@sveltejs/adapter-static": "^3.0.10", + "@sveltejs/kit": "^2.48.4", + "@sveltejs/vite-plugin-svelte": "^6.2.1", "@tailwindcss/forms": "^0.5.9", "@tailwindcss/typography": "^0.5.15", "@tailwindcss/vite": "^4.0.0", @@ -48,21 +48,21 @@ "dexie": "^4.0.11", "eslint": "^9.18.0", "eslint-config-prettier": "^10.0.1", - "eslint-plugin-storybook": "^9.0.17", + "eslint-plugin-storybook": "^10.0.7", "eslint-plugin-svelte": "^3.0.0", "fflate": "^0.8.2", "globals": "^16.0.0", "http-server": "^14.1.1", "mdast": "^3.0.0", "mdsvex": "^0.12.3", - "playwright": "^1.53.0", + "playwright": "^1.56.1", "prettier": "^3.4.2", "prettier-plugin-svelte": "^3.3.3", "prettier-plugin-tailwindcss": "^0.6.11", "rehype-katex": "^7.0.1", "remark-math": "^6.0.0", "sass": "^1.93.3", - "storybook": "^9.0.17", + "storybook": "^10.0.7", "svelte": "^5.0.0", "svelte-check": "^4.0.0", "tailwind-merge": "^3.3.1", @@ -73,7 +73,7 @@ "typescript-eslint": "^8.20.0", "unified": "^11.0.5", "uuid": "^13.0.0", - "vite": "^7.0.4", + "vite": "^7.2.2", "vite-plugin-devtools-json": "^0.2.0", "vitest": "^3.2.3", "vitest-browser-svelte": "^0.1.0" diff --git a/tools/server/webui/src/stories/ChatForm.stories.svelte b/tools/server/webui/src/stories/ChatForm.stories.svelte index 6a0fc08701..82848e4fbf 100644 --- a/tools/server/webui/src/stories/ChatForm.stories.svelte +++ b/tools/server/webui/src/stories/ChatForm.stories.svelte @@ -1,7 +1,7 @@