Sync master with upstream release b9010

.github/ISSUE_TEMPLATE/010-bug-compilation.yml

@@ -12,6 +12,8 @@ body:
         after recreating the CMake build directory and with `-DGGML_CCACHE=OFF`.
         If the compilation succeeds with ccache disabled you should be able to permanently fix the issue
         by clearing `~/.cache/ccache` (on Linux).
+
+        Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
   - type: textarea
     id: commit
     attributes:

.github/ISSUE_TEMPLATE/011-bug-results.yml

@@ -1,5 +1,5 @@
 name: Bug (model use)
-description: Something goes wrong when using a model (in general, not specific to a single llama.cpp module).
+description: Something goes wrong when running a model (crashes, garbled outputs, etc.).
 title: "Eval bug: "
 labels: ["bug-unconfirmed", "model evaluation"]
 body:
@@ -12,6 +12,8 @@ body:
         If you encountered the issue while using an external UI (e.g. ollama),
         please reproduce your issue using one of the examples/binaries in this repository.
         The `llama-completion` binary can be used for simple and reproducible model inference.
+
+        Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
   - type: textarea
     id: version
     attributes:

.github/ISSUE_TEMPLATE/019-bug-misc.yml

@@ -10,6 +10,8 @@ body:
         This issue template is intended for miscellaneous bugs that don't fit into any other category.
         If you encountered the issue while using an external UI (e.g. ollama),
         please reproduce your issue using one of the examples/binaries in this repository.
+
+        Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
   - type: textarea
     id: version
     attributes:

.github/ISSUE_TEMPLATE/020-enhancement.yml

@@ -8,6 +8,8 @@ body:
       value: |
         [Please post your idea first in Discussion if there is not yet a consensus for this enhancement request. This will help to keep this issue tracker focused on enhancements that the community has agreed needs to be implemented.](https://github.com/ggml-org/llama.cpp/discussions/categories/ideas)
 
+        Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
+
   - type: checkboxes
     id: prerequisites
     attributes:

.github/ISSUE_TEMPLATE/030-research.yml

@@ -8,6 +8,8 @@ body:
       value: |
         Don't forget to check for any [duplicate research issue tickets](https://github.com/ggml-org/llama.cpp/issues?q=is%3Aopen+is%3Aissue+label%3A%22research+%F0%9F%94%AC%22)
 
+        Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
+
   - type: checkboxes
     id: research-stage
     attributes:

.github/ISSUE_TEMPLATE/040-refactor.yml

@@ -9,6 +9,8 @@ body:
         Don't forget to [check for existing refactor issue tickets](https://github.com/ggml-org/llama.cpp/issues?q=is%3Aopen+is%3Aissue+label%3Arefactoring) in case it's already covered.
         Also you may want to check [Pull request refactor label as well](https://github.com/ggml-org/llama.cpp/pulls?q=is%3Aopen+is%3Apr+label%3Arefactoring) for duplicates too.
 
+        Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
+
   - type: textarea
     id: background-description
     attributes:

convert_hf_to_gguf.py

@@ -13232,17 +13232,18 @@ class LazyTorchTensor(gguf.LazyBase):
     }
 
     # only used when byteswapping data. Only correct size is needed
+    # TODO: uncomment uint64, uint32, and uint16, ref: https://github.com/pytorch/pytorch/issues/58734
     _dtype_byteswap_map: dict[torch.dtype, type] = {
         torch.float64: np.float64,
         torch.float32: np.float32,
         torch.bfloat16: np.float16,
         torch.float16: np.float16,
         torch.int64: np.int64,
-        torch.uint64: np.uint64,
+        # torch.uint64: np.uint64,
         torch.int32: np.int32,
-        torch.uint32: np.uint32,
+        # torch.uint32: np.uint32,
         torch.int16: np.int16,
-        torch.uint16: np.uint16,
+        # torch.uint16: np.uint16,
         torch.int8: np.int8,
         torch.uint8: np.uint8,
         torch.bool: np.uint8,

ggml/CMakeLists.txt

@@ -5,7 +5,7 @@ project("ggml" C CXX ASM)
 ### GGML Version
 set(GGML_VERSION_MAJOR 0)
 set(GGML_VERSION_MINOR 10)
-set(GGML_VERSION_PATCH 1)
+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/")

ggml/src/ggml-cuda/ggml-cuda.cu

@@ -5431,8 +5431,8 @@ ggml_backend_reg_t ggml_backend_cuda_reg() {
                 CUDA_CHECK(cudaGetDeviceProperties(&prop, i));
                 dev_ctx->description = prop.name;
 
-                char pci_bus_id[16] = {};
-                snprintf(pci_bus_id, sizeof(pci_bus_id), "%04x:%02x:%02x.0", prop.pciDomainID, prop.pciBusID, prop.pciDeviceID);
+                char pci_bus_id[32] = {};
+                CUDA_CHECK(cudaDeviceGetPCIBusId(pci_bus_id, sizeof(pci_bus_id), i));
                 dev_ctx->pci_bus_id = pci_bus_id;
                 dev_ctx->op_offload_min_batch_size = min_batch_size;
 

ggml/src/ggml-cuda/vendors/hip.h

@@ -55,6 +55,7 @@
 #define cudaDeviceDisablePeerAccess hipDeviceDisablePeerAccess
 #define cudaDeviceEnablePeerAccess hipDeviceEnablePeerAccess
 #define cudaDeviceGetAttribute hipDeviceGetAttribute
+#define cudaDeviceGetPCIBusId hipDeviceGetPCIBusId
 #define cudaDeviceProp hipDeviceProp_t
 #define cudaDeviceSynchronize hipDeviceSynchronize
 #define cudaError_t hipError_t

ggml/src/ggml-cuda/vendors/musa.h

@@ -39,6 +39,7 @@
 #define cudaDeviceCanAccessPeer musaDeviceCanAccessPeer
 #define cudaDeviceDisablePeerAccess musaDeviceDisablePeerAccess
 #define cudaDeviceEnablePeerAccess musaDeviceEnablePeerAccess
+#define cudaDeviceGetPCIBusId musaDeviceGetPCIBusId
 #define cudaDeviceProp musaDeviceProp
 #define cudaDeviceSynchronize musaDeviceSynchronize
 #define cudaError_t musaError_t

ggml/src/ggml-hexagon/CMakeLists.txt

@@ -22,7 +22,8 @@ message(STATUS "hexagon: using ${HEXAGON_SDK_ROOT} and ${HEXAGON_TOOLS_ROOT} for
 include(${HEXAGON_SDK_ROOT}/build/cmake/hexagon_fun.cmake)
 include(ExternalProject)
 
-option(GGML_HEXAGON_HTP_DEBUG "ggml-hexagon: enable HTP debug output" OFF)
+option(GGML_HEXAGON_HTP_DEBUG  "ggml-hexagon: enable HTP debug output" OFF)
+option(GGML_HEXAGON_FA_EXP2_HF "ggml-hexagon: use FP16 exp2 polynomial in FA softmax instead of F32 exp round-trip" OFF)
 set(GGML_HEXAGON_HTP_CERT  "$ENV{HEXAGON_HTP_CERT}" CACHE PATH "ggml-hexagon: enable HTP library signing using certificate")
 set(GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE 128 CACHE STRING "ggml-hexagon: quantize group size (32, 64, or 128)")
 

ggml/src/ggml-hexagon/ggml-hexagon.cpp

@@ -2254,8 +2254,7 @@ static bool ggml_hexagon_supported_flash_attn_ext(const struct ggml_hexagon_sess
         return false;
     }
 
-    if (dst->ne[2] != 1 || dst->ne[3] != 1) {
-        // FA during prompt still needs work
+    if (dst->ne[3] != 1) {
         return false;
     }
 

ggml/src/ggml-hexagon/htp/CMakeLists.txt

@@ -44,6 +44,11 @@ target_compile_definitions(${HTP_LIB} PRIVATE
     $<IF:$<BOOL:${HEXAGON_HTP_DEBUG}>,FARF_HIGH=1,>
     FP32_QUANTIZE_GROUP_SIZE=${GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE})
 
+if (GGML_HEXAGON_FA_EXP2_HF)
+    message(STATUS "ggml-htp: HMX_FA_USE_EXP2_HF=1 (use FP16 exp2 polynomial in FA softmax)")
+    target_compile_definitions(${HTP_LIB} PRIVATE HMX_FA_USE_EXP2_HF=1)
+endif()
+
 # HMX acceleration: available on v73+ architectures
 set(HTP_HMX_VERSIONS v73 v75 v79 v81)
 list(FIND HTP_HMX_VERSIONS ${DSP_VERSION} _hmx_idx)
@@ -52,11 +57,13 @@ if (_hmx_idx GREATER_EQUAL 0)
     target_sources(${HTP_LIB} PRIVATE
         hmx-queue.c
         hmx-matmul-ops.c
+        hmx-flash-attn-ops.c
     )
 
     # -mhmx enables HMX instruction set (needed by files that include hmx-utils.h)
     set_source_files_properties(
         hmx-matmul-ops.c
+        hmx-flash-attn-ops.c
         PROPERTIES COMPILE_OPTIONS "-mhmx"
     )
 

ggml/src/ggml-hexagon/htp/cmake-toolchain.cmake

@@ -138,15 +138,15 @@ set(CMAKE_SHARED_LIBRARY_SONAME_C_FLAG   "-Wl,-soname,")
 set(CMAKE_SHARED_LIBRARY_SONAME_CXX_FLAG "-Wl,-soname,")
 
 #Compiler Options
-set(COMMON_FLAGS "-mcpu=hexagon${V_ARCH} -m${V_ARCH} -mhvx=${V_ARCH} -fvectorize -Wall -Werror -fno-zero-initialized-in-bss -G0 -fdata-sections -fpic ${XQF_ARGS}")
+set(COMMON_FLAGS "-mcpu=hexagon${V_ARCH} -m${V_ARCH} -mhvx=${V_ARCH} -fvectorize -flto -Wall -Werror -fno-zero-initialized-in-bss -G0 -fdata-sections -fpic ${XQF_ARGS}")
 
 set(CMAKE_CXX_FLAGS_DEBUG          "${COMMON_FLAGS} -O0 -D_DEBUG -g")
-set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "${COMMON_FLAGS} -O3 -g")
-set(CMAKE_CXX_FLAGS_RELEASE        "${COMMON_FLAGS} -O3")
+set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "${COMMON_FLAGS} -O2 -g")
+set(CMAKE_CXX_FLAGS_RELEASE        "${COMMON_FLAGS} -O2")
 
 set(CMAKE_C_FLAGS_DEBUG            "${COMMON_FLAGS} -O0 -D_DEBUG -g")
-set(CMAKE_C_FLAGS_RELWITHDEBINFO   "${COMMON_FLAGS} -O3 -g")
-set(CMAKE_C_FLAGS_RELEASE          "${COMMON_FLAGS} -O3")
+set(CMAKE_C_FLAGS_RELWITHDEBINFO   "${COMMON_FLAGS} -O2 -g")
+set(CMAKE_C_FLAGS_RELEASE          "${COMMON_FLAGS} -O2")
 
 set(CMAKE_ASM_FLAGS_DEBUG          "${COMMON_FLAGS} ${CMAKE_CXX_FLAGS_DEBUG}")
 set(CMAKE_ASM_FLAGS_RELEASE        "${COMMON_FLAGS} ${CMAKE_CXX_FLAGS_RELEASE}")

ggml/src/ggml-hexagon/htp/flash-attn-ops.c

@@ -17,13 +17,14 @@
 #include "htp-ctx.h"
 #include "htp-ops.h"
 #include "htp-ops.h"
+#include "hmx-ops.h"
 
 // Must be multiple of 32
 #define FLASH_ATTN_BLOCK_SIZE (32 * 2)
 
 // This is a bit of a hack because the compiler is strugling to properly inline
 // the default hvx_vec_f32_to_f16 with output into the local array.
-static void __attribute__((noinline)) hvx_vec_f32_to_f16_a(void *ptr, HVX_Vector v0, HVX_Vector v1)
+static __attribute__((noinline)) void hvx_vec_f32_to_f16_a(void *ptr, HVX_Vector v0, HVX_Vector v1)
 {
     *(HVX_Vector *) ptr = hvx_vec_f32_to_f16(v0, v1);
 }
@@ -621,6 +622,17 @@ int op_flash_attn_ext(struct htp_ops_context * octx) {
         return HTP_STATUS_NO_SUPPORT;
     }
 
+#ifdef HTP_HAS_HMX
+    // HMX path: prefill (neq1 >= 32), head_dim multiple of 32, F16 KV
+    if (k->type == HTP_TYPE_F16 && v->type == HTP_TYPE_F16 && k->ne[0] % 32 == 0 && q->ne[1] >= 32) {
+        int ret = hmx_flash_attn_ext(octx);
+        if (ret == HTP_STATUS_OK) {
+            return ret;
+        }
+        // VTCM too small or other failure -> fall through to HVX path
+    }
+#endif
+
     struct htp_fa_context factx;
     factx.octx = octx;
 

ggml/src/ggml-hexagon/htp/hex-utils.h

@@ -74,6 +74,12 @@ static inline size_t hex_smax(size_t a, size_t b) {
     return a > b ? a : b;
 }
 
+static inline void hex_swap_ptr(void ** p1, void ** p2) {
+    void * t = *p1;
+    *p1      = *p2;
+    *p2      = t;
+}
+
 static inline void hex_l2fetch(const void * p, uint32_t width, uint32_t stride, uint32_t height) {
     const uint64_t control = Q6_P_combine_RR(stride, Q6_R_combine_RlRl(width, height));
     Q6_l2fetch_AP((void *) p, control);