sync ggml v0.15.2

.github/workflows/native-ci.yml

@@ -198,7 +198,7 @@ jobs:
         run: |
           sudo apt-get update
           sudo apt-get install -y cmake ninja-build zlib1g-dev \
-            libvulkan-dev glslc patchelf ccache
+            libvulkan-dev glslc spirv-headers patchelf ccache
       - name: CPU ISA signature (segregates ccache across the heterogeneous fleet)
         # ggml builds with -march=native here (the dev posture under test);
         # ccache hashes the literal flag, not the ISA it resolves to, so a

ggml/CMakeLists.txt

@@ -1,12 +1,15 @@
 cmake_minimum_required(VERSION 3.14...3.28) # for add_link_options and implicit target directories.
+
 project("ggml" C CXX ASM)
 
 ### GGML Version
 set(GGML_VERSION_MAJOR 0)
-set(GGML_VERSION_MINOR 9)
-set(GGML_VERSION_PATCH 8)
+set(GGML_VERSION_MINOR 15)
+set(GGML_VERSION_PATCH 2)
 set(GGML_VERSION_BASE "${GGML_VERSION_MAJOR}.${GGML_VERSION_MINOR}.${GGML_VERSION_PATCH}")
 
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake/")
+
 find_program(GIT_EXE NAMES git git.exe NO_CMAKE_FIND_ROOT_PATH)
 if(GIT_EXE)
     # Get current git commit hash
@@ -166,15 +169,16 @@ if (NOT MSVC)
     option(GGML_AMX_INT8     "ggml: enable AMX-INT8"         OFF)
     option(GGML_AMX_BF16     "ggml: enable AMX-BF16"         OFF)
 endif()
-option(GGML_LASX             "ggml: enable lasx"             ON)
-option(GGML_LSX              "ggml: enable lsx"              ON)
-option(GGML_RVV              "ggml: enable rvv"              ON)
-option(GGML_RV_ZFH           "ggml: enable riscv zfh"        ON)
-option(GGML_RV_ZVFH          "ggml: enable riscv zvfh"       ON)
-option(GGML_RV_ZICBOP        "ggml: enable riscv zicbop"     ON)
-option(GGML_RV_ZIHINTPAUSE   "ggml: enable riscv zihintpause "  ON)
-option(GGML_XTHEADVECTOR     "ggml: enable xtheadvector"     OFF)
-option(GGML_VXE              "ggml: enable vxe"              ${GGML_NATIVE})
+option(GGML_LASX             "ggml: enable lasx"              ON)
+option(GGML_LSX              "ggml: enable lsx"               ON)
+option(GGML_RVV              "ggml: enable rvv"               ON)
+option(GGML_RV_ZFH           "ggml: enable riscv zfh"         ON)
+option(GGML_RV_ZVFH          "ggml: enable riscv zvfh"        ON)
+option(GGML_RV_ZICBOP        "ggml: enable riscv zicbop"      ON)
+option(GGML_RV_ZIHINTPAUSE   "ggml: enable riscv zihintpause" ON)
+option(GGML_RV_ZVFBFWMA      "ggml: enable riscv zvfbfwma"    OFF)
+option(GGML_XTHEADVECTOR     "ggml: enable xtheadvector"      OFF)
+option(GGML_VXE              "ggml: enable vxe"               ${GGML_NATIVE})
 
 option(GGML_CPU_ALL_VARIANTS "ggml: build all variants of the CPU backend (requires GGML_BACKEND_DL)" OFF)
 set(GGML_CPU_ARM_ARCH        "" CACHE STRING "ggml: CPU architecture for ARM")
@@ -203,12 +207,14 @@ option(GGML_CUDA_NO_VMM                     "ggml: do not try to use CUDA VMM"
 option(GGML_CUDA_FA                         "ggml: compile ggml FlashAttention CUDA kernels"  ON)
 option(GGML_CUDA_FA_ALL_QUANTS              "ggml: compile all quants for FlashAttention"     OFF)
 option(GGML_CUDA_GRAPHS                     "ggml: use CUDA graphs (llama.cpp only)"          ${GGML_CUDA_GRAPHS_DEFAULT})
+option(GGML_CUDA_NCCL                       "ggml: use NVIDIA Collective Comm. Library"       ON)
 set   (GGML_CUDA_COMPRESSION_MODE "size" CACHE STRING
                                             "ggml: cuda link binary compression mode; requires cuda 12.8+")
 set_property(CACHE GGML_CUDA_COMPRESSION_MODE PROPERTY STRINGS "none;speed;balance;size")
 
 option(GGML_HIP                             "ggml: use HIP"                                   OFF)
-option(GGML_HIP_GRAPHS                      "ggml: use HIP graph, experimental, slow"         OFF)
+option(GGML_HIP_GRAPHS                      "ggml: use HIP graph"                              ON)
+option(GGML_HIP_RCCL                        "ggml: use ROCm Collective Comm. Library"         OFF)
 option(GGML_HIP_NO_VMM                      "ggml: do not try to use HIP VMM"                 ON)
 option(GGML_HIP_ROCWMMA_FATTN               "ggml: enable rocWMMA for FlashAttention"         OFF)
 option(GGML_HIP_MMQ_MFMA                    "ggml: enable MFMA MMA for CDNA in MMQ"           ON)
@@ -242,6 +248,8 @@ option(GGML_RPC                             "ggml: use RPC"
 option(GGML_SYCL                            "ggml: use SYCL"                                  OFF)
 option(GGML_SYCL_F16                        "ggml: use 16 bit floats for sycl calculations"   OFF)
 option(GGML_SYCL_GRAPH                      "ggml: enable graphs in the SYCL backend"         ON)
+option(GGML_SYCL_HOST_MEM_FALLBACK          "ggml: allow host memory fallback in SYCL reorder (requires kernel 6.8+)" ON)
+option(GGML_SYCL_SUPPORT_LEVEL_ZERO_API     "ggml: use Level Zero API in SYCL backend"  ON)
 option(GGML_SYCL_DNN                        "ggml: enable oneDNN in the SYCL backend"         ON)
 set   (GGML_SYCL_TARGET "INTEL" CACHE STRING
                                             "ggml: sycl target device")
@@ -345,7 +353,7 @@ if (GGML_STANDALONE)
         @ONLY)
 
     install(FILES ${CMAKE_CURRENT_BINARY_DIR}/ggml.pc
-        DESTINATION share/pkgconfig)
+        DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
 endif()
 
 #

ggml/UPSTREAM

@@ -1,8 +1,8 @@
 repo: https://github.com/ggml-org/ggml
-sha:  404fcb9d7c96989569e68c9e7881ee3465a05c50
+sha:  707321c4cf6d21cb4bc831aa8b687dbf01a521ce
 
 This directory is a vendored snapshot of ggml at the SHA above. Do not edit
-files in this directory by hand. To pick up upstream changes, re-clone
-ggml-org/ggml at a new SHA, replace this directory wholesale, and update the
-sha line above. A scripts/sync-ggml.sh helper will be added when the sync
-workflow is needed.
+files in this directory by hand; local changes are overwritten on the next sync.
+To move the snapshot, run scripts/sync-ggml.sh <ref> from the repo root: it
+re-vendors this directory and rewrites this file. The snapshot is upstream's
+tracked tree at the SHA, minus .github/ (upstream CI, irrelevant to a vendor).

ggml/cmake/FindNCCL.cmake

@@ -0,0 +1,36 @@
+# cmake/FindNCCL.cmake
+
+# NVIDIA does not distribute CMake files with NCCl, therefore use this file to find it instead.
+
+find_path(NCCL_INCLUDE_DIR
+    NAMES nccl.h
+    HINTS ${NCCL_ROOT} $ENV{NCCL_ROOT} $ENV{CUDA_HOME} /usr/local/cuda
+    PATH_SUFFIXES include
+)
+
+find_library(NCCL_LIBRARY
+    NAMES nccl
+    HINTS ${NCCL_ROOT} $ENV{NCCL_ROOT} $ENV{CUDA_HOME} /usr/local/cuda
+    PATH_SUFFIXES lib lib64
+)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(NCCL
+    DEFAULT_MSG
+    NCCL_LIBRARY NCCL_INCLUDE_DIR
+)
+
+if(NCCL_FOUND)
+    set(NCCL_LIBRARIES ${NCCL_LIBRARY})
+    set(NCCL_INCLUDE_DIRS ${NCCL_INCLUDE_DIR})
+
+    if(NOT TARGET NCCL::NCCL)
+        add_library(NCCL::NCCL UNKNOWN IMPORTED)
+        set_target_properties(NCCL::NCCL PROPERTIES
+            IMPORTED_LOCATION "${NCCL_LIBRARY}"
+            INTERFACE_INCLUDE_DIRECTORIES "${NCCL_INCLUDE_DIR}"
+        )
+    endif()
+endif()
+
+mark_as_advanced(NCCL_INCLUDE_DIR NCCL_LIBRARY)

ggml/cmake/ggml-config.cmake.in

@@ -6,6 +6,7 @@
 include(CMakeFindDependencyMacro)
 find_dependency(Threads)
 if (NOT GGML_SHARED_LIB)
+    set(GGML_BASE_INTERFACE_LINK_LIBRARIES "")
     set(GGML_CPU_INTERFACE_LINK_LIBRARIES "")
     set(GGML_CPU_INTERFACE_LINK_OPTIONS   "")
 
@@ -20,7 +21,15 @@ if (NOT GGML_SHARED_LIB)
 
     if (GGML_OPENMP_ENABLED)
         find_dependency(OpenMP)
-        list(APPEND GGML_CPU_INTERFACE_LINK_LIBRARIES OpenMP::OpenMP_C OpenMP::OpenMP_CXX)
+        set(GGML_OPENMP_INTERFACE_LINK_LIBRARIES "")
+        if (TARGET OpenMP::OpenMP_C)
+            list(APPEND GGML_OPENMP_INTERFACE_LINK_LIBRARIES OpenMP::OpenMP_C)
+        endif()
+        if (TARGET OpenMP::OpenMP_CXX)
+            list(APPEND GGML_OPENMP_INTERFACE_LINK_LIBRARIES OpenMP::OpenMP_CXX)
+        endif()
+        list(APPEND GGML_BASE_INTERFACE_LINK_LIBRARIES ${GGML_OPENMP_INTERFACE_LINK_LIBRARIES})
+        list(APPEND GGML_CPU_INTERFACE_LINK_LIBRARIES ${GGML_OPENMP_INTERFACE_LINK_LIBRARIES})
     endif()
 
     if (GGML_CPU_HBM)
@@ -122,7 +131,8 @@ if(NOT TARGET ggml::ggml)
     add_library(ggml::ggml-base UNKNOWN IMPORTED)
     set_target_properties(ggml::ggml-base
         PROPERTIES
-            IMPORTED_LOCATION "${GGML_BASE_LIBRARY}")
+            IMPORTED_LOCATION "${GGML_BASE_LIBRARY}"
+            INTERFACE_LINK_LIBRARIES "${GGML_BASE_INTERFACE_LINK_LIBRARIES}")
 
     set(_ggml_all_targets "")
     if (NOT GGML_BACKEND_DL)

ggml/docs/gguf.md

@@ -20,9 +20,12 @@ The key difference between GGJT and GGUF is the use of a key-value structure for
 
 ### GGUF Naming Convention
 
-GGUF follow a naming convention of `<BaseName><SizeLabel><FineTune><Version><Encoding><Type><Shard>.gguf` where each component is delimitated by a `-` if present. Ultimately this is intended to make it easier for humans to at a glance get the most important details of a model. It is not intended to be perfectly parsable in the field due to the diversity of existing gguf filenames.
+GGUF follow a naming convention of `[<Sidecar>]<BaseName><SizeLabel><FineTune><Version><Encoding><Type><Shard>.gguf` where each component is delimitated by a `-` if present. Ultimately this is intended to make it easier for humans to at a glance get the most important details of a model. It is not intended to be perfectly parsable in the field due to the diversity of existing gguf filenames.
 
 The components are:
+1. **Sidecar**: (Optional) Prefix marking the file as an auxiliary module loaded alongside a base model, rather than a standalone model. When present, sits at the very front of the filename followed by `-`. Lowercase by convention.
+    - `mmproj` : Multimodal projector (vision/audio encoder and projection layer for use with a base LLM)
+    - `mtp` : Multi-Token Prediction heads (speculative-decoding draft module, intended to be loaded alongside a base model of matching architecture and version). Note that oftentimes the MTP weights can be distributed inside the base model, in which case there is no separate `mtp-` sidecar file.
 1. **BaseName**: A descriptive name for the model base type or architecture.
     - This can be derived from gguf metadata `general.basename` substituting spaces for dashes.
 1. **SizeLabel**: Parameter weight class (useful for leader boards) represented as `<expertCount>x<count><scale-prefix>`
@@ -54,7 +57,7 @@ The components are:
 
 At a minimum all model files should have at least BaseName, SizeLabel, Version, in order to be easily validated as a file that is keeping with the GGUF Naming Convention. An example of this issue is that it is easy for Encoding to be mistaken as a FineTune if Version is omitted.
 
-To validate you can use this regular expression `^(?<BaseName>[A-Za-z0-9\s]*(?:(?:-(?:(?:[A-Za-z\s][A-Za-z0-9\s]*)|(?:[0-9\s]*)))*))-(?:(?<SizeLabel>(?:\d+x)?(?:\d+\.)?\d+[A-Za-z](?:-[A-Za-z]+(\d+\.)?\d+[A-Za-z]+)?)(?:-(?<FineTune>[A-Za-z0-9\s-]+))?)?-(?:(?<Version>v\d+(?:\.\d+)*))(?:-(?<Encoding>(?!LoRA|vocab)[\w_]+))?(?:-(?<Type>LoRA|vocab))?(?:-(?<Shard>\d{5}-of-\d{5}))?\.gguf$` which will check that you got the minimum BaseName, SizeLabel and Version present in the correct order.
+To validate you can use this regular expression `^(?:(?<Sidecar>mmproj|mtp)-)?(?<BaseName>[A-Za-z0-9\s]*(?:(?:-(?:(?:[A-Za-z\s][A-Za-z0-9\s]*)|(?:[0-9\s]*)))*))-(?:(?<SizeLabel>(?:\d+x)?(?:\d+\.)?\d+[A-Za-z](?:-[A-Za-z]+(\d+\.)?\d+[A-Za-z]+)?)(?:-(?<FineTune>[A-Za-z0-9\s-]+))?)?-(?:(?<Version>v\d+(?:\.\d+)*))(?:-(?<Encoding>(?!LoRA|vocab)[\w_]+))?(?:-(?<Type>LoRA|vocab))?(?:-(?<Shard>\d{5}-of-\d{5}))?\.gguf$` which will check that you got the minimum BaseName, SizeLabel and Version present in the correct order.
 
 For example:
 
@@ -81,26 +84,44 @@ For example:
     - Weight Encoding Scheme: Q4_0
     - Shard: 3 out of 9 total shards
 
+  * `mtp-Qwen3-27B-v1.0-Q4_K_M.gguf`
+    - Sidecar: mtp (Multi-Token Prediction draft module)
+    - Model Name: Qwen3
+    - Expert Count: 0
+    - Parameter Count: 27B (of the main model — sidecar tensors are smaller)
+    - Version Number: v1.0
+    - Weight Encoding Scheme: Q4_K_M
+
+  * `mmproj-Qwen2-VL-7B-v1.0-F16.gguf`
+    - Sidecar: mmproj (multimodal projector)
+    - Model Name: Qwen2-VL
+    - Expert Count: 0
+    - Parameter Count: 7B (of the main model — sidecar tensors are smaller)
+    - Version Number: v1.0
+    - Weight Encoding Scheme: F16
+
 
 <details><summary>Example Node.js Regex Function</summary>
 
 ```js
 #!/usr/bin/env node
-const ggufRegex = /^(?<BaseName>[A-Za-z0-9\s]*(?:(?:-(?:(?:[A-Za-z\s][A-Za-z0-9\s]*)|(?:[0-9\s]*)))*))-(?:(?<SizeLabel>(?:\d+x)?(?:\d+\.)?\d+[A-Za-z](?:-[A-Za-z]+(\d+\.)?\d+[A-Za-z]+)?)(?:-(?<FineTune>[A-Za-z0-9\s-]+))?)?-(?:(?<Version>v\d+(?:\.\d+)*))(?:-(?<Encoding>(?!LoRA|vocab)[\w_]+))?(?:-(?<Type>LoRA|vocab))?(?:-(?<Shard>\d{5}-of-\d{5}))?\.gguf$/;
+const ggufRegex = /^(?:(?<Sidecar>mmproj|mtp)-)?(?<BaseName>[A-Za-z0-9\s]*(?:(?:-(?:(?:[A-Za-z\s][A-Za-z0-9\s]*)|(?:[0-9\s]*)))*))-(?:(?<SizeLabel>(?:\d+x)?(?:\d+\.)?\d+[A-Za-z](?:-[A-Za-z]+(\d+\.)?\d+[A-Za-z]+)?)(?:-(?<FineTune>[A-Za-z0-9\s-]+))?)?-(?:(?<Version>v\d+(?:\.\d+)*))(?:-(?<Encoding>(?!LoRA|vocab)[\w_]+))?(?:-(?<Type>LoRA|vocab))?(?:-(?<Shard>\d{5}-of-\d{5}))?\.gguf$/;
 
 function parseGGUFFilename(filename) {
   const match = ggufRegex.exec(filename);
   if (!match)
     return null;
-  const {BaseName = null, SizeLabel = null, FineTune = null, Version = "v1.0", Encoding = null, Type = null, Shard = null} = match.groups;
-  return {BaseName: BaseName, SizeLabel: SizeLabel, FineTune: FineTune, Version: Version, Encoding: Encoding, Type: Type, Shard: Shard};
+  const {Sidecar = null, BaseName = null, SizeLabel = null, FineTune = null, Version = "v1.0", Encoding = null, Type = null, Shard = null} = match.groups;
+  return {Sidecar: Sidecar, BaseName: BaseName, SizeLabel: SizeLabel, FineTune: FineTune, Version: Version, Encoding: Encoding, Type: Type, Shard: Shard};
 }
 
 const testCases = [
-  {filename: 'Mixtral-8x7B-v0.1-KQ2.gguf',                         expected: { BaseName: 'Mixtral',              SizeLabel: '8x7B',     FineTune: null, Version: 'v0.1',   Encoding: 'KQ2',  Type: null, Shard: null}},
-  {filename: 'Grok-100B-v1.0-Q4_0-00003-of-00009.gguf',            expected: { BaseName: 'Grok',                 SizeLabel: '100B',     FineTune: null, Version: 'v1.0',   Encoding: 'Q4_0', Type: null, Shard: "00003-of-00009"}},
-  {filename: 'Hermes-2-Pro-Llama-3-8B-v1.0-F16.gguf',              expected: { BaseName: 'Hermes-2-Pro-Llama-3', SizeLabel: '8B', FineTune: null, Version: 'v1.0',   Encoding: 'F16',  Type: null, Shard: null}},
-  {filename: 'Phi-3-mini-3.8B-ContextLength4k-instruct-v1.0.gguf', expected: { BaseName: 'Phi-3-mini',   SizeLabel: '3.8B-ContextLength4k', FineTune: 'instruct', Version: 'v1.0',   Encoding: null,  Type: null, Shard: null}},
+  {filename: 'Mixtral-8x7B-v0.1-KQ2.gguf',                         expected: { Sidecar: null,   BaseName: 'Mixtral',              SizeLabel: '8x7B',     FineTune: null, Version: 'v0.1',   Encoding: 'KQ2',    Type: null, Shard: null}},
+  {filename: 'Grok-100B-v1.0-Q4_0-00003-of-00009.gguf',            expected: { Sidecar: null,   BaseName: 'Grok',                 SizeLabel: '100B',     FineTune: null, Version: 'v1.0',   Encoding: 'Q4_0',   Type: null, Shard: "00003-of-00009"}},
+  {filename: 'Hermes-2-Pro-Llama-3-8B-v1.0-F16.gguf',              expected: { Sidecar: null,   BaseName: 'Hermes-2-Pro-Llama-3', SizeLabel: '8B',       FineTune: null, Version: 'v1.0',   Encoding: 'F16',    Type: null, Shard: null}},
+  {filename: 'Phi-3-mini-3.8B-ContextLength4k-instruct-v1.0.gguf', expected: { Sidecar: null,   BaseName: 'Phi-3-mini',           SizeLabel: '3.8B-ContextLength4k', FineTune: 'instruct', Version: 'v1.0', Encoding: null,    Type: null, Shard: null}},
+  {filename: 'mtp-Qwen3-27B-v1.0-Q4_K_M.gguf',                     expected: { Sidecar: 'mtp',  BaseName: 'Qwen3',                SizeLabel: '27B',      FineTune: null, Version: 'v1.0',   Encoding: 'Q4_K_M', Type: null, Shard: null}},
+  {filename: 'mmproj-Qwen2-VL-7B-v1.0-F16.gguf',                   expected: { Sidecar: 'mmproj', BaseName: 'Qwen2-VL',           SizeLabel: '7B',       FineTune: null, Version: 'v1.0',   Encoding: 'F16',    Type: null, Shard: null}},
   {filename: 'not-a-known-arrangement.gguf',                       expected: null},
 ];
 

ggml/examples/common-ggml.cpp

@@ -74,6 +74,7 @@ bool ggml_common_quantize_0(
         case GGML_FTYPE_MOSTLY_BF16:
         case GGML_FTYPE_MOSTLY_MXFP4:
         case GGML_FTYPE_MOSTLY_NVFP4:
+        case GGML_FTYPE_MOSTLY_Q1_0:
                 {
                     fprintf(stderr, "%s: invalid model type %d\n", __func__, ftype);
                     return false;
@@ -215,6 +216,7 @@ bool ggml_common_quantize_0(
                 case GGML_TYPE_TQ2_0:
                 case GGML_TYPE_MXFP4:
                 case GGML_TYPE_NVFP4:
+                case GGML_TYPE_Q1_0:
                 case GGML_TYPE_COUNT:
                     {
                         fprintf(stderr, "%s: unsupported quantization type %d (%s)\n", __func__, ttype, ggml_type_name((ggml_type) ttype));

ggml/examples/sam/sam.cpp

@@ -2230,6 +2230,7 @@ bool sam_params_parse(int argc, char ** argv, sam_params & params) {
 
 
 int main(int argc, char ** argv) {
+    ggml_time_init();
     const int64_t t_main_start_us = ggml_time_us();
 
     sam_params params;

ggml/include/ggml-alloc.h

@@ -76,6 +76,7 @@ GGML_API size_t ggml_gallocr_get_buffer_size(ggml_gallocr_t galloc, int buffer_i
 // Utils
 // Create a buffer and allocate all the tensors in a ggml_context
 // ggml_backend_alloc_ctx_tensors_from_buft_size returns the size of the buffer that would be allocated by ggml_backend_alloc_ctx_tensors_from_buft
+// ggml_backend_alloc_ctx_tensors_from_buft returns NULL on failure or if all tensors in ctx are already allocated or zero-sized
 GGML_API size_t                       ggml_backend_alloc_ctx_tensors_from_buft_size(struct ggml_context * ctx, ggml_backend_buffer_type_t buft);
 GGML_API struct ggml_backend_buffer * ggml_backend_alloc_ctx_tensors_from_buft(struct ggml_context * ctx, ggml_backend_buffer_type_t buft);
 GGML_API struct ggml_backend_buffer * ggml_backend_alloc_ctx_tensors(struct ggml_context * ctx, ggml_backend_t backend);