Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	docs/backend/SYCL.md
#	ggml/src/ggml-cpu/ggml-cpu.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-opencl/kernels/gemv_moe_mxfp4_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemv_moe_q4_k_f32_ns.cl
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/test-alloc.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-gguf.cpp
#	tests/test-save-load-state.cpp
This commit is contained in:
Concedo 2026-07-13 20:53:37 +08:00
commit fa21872f97
76 changed files with 1399 additions and 1110 deletions

View file

@ -8,10 +8,10 @@ extern "C" {
#define RPC_PROTO_MAJOR_VERSION 4
#define RPC_PROTO_MINOR_VERSION 0
#define RPC_PROTO_PATCH_VERSION 1
#define RPC_PROTO_PATCH_VERSION 2
#ifdef __cplusplus
static_assert(GGML_OP_COUNT == 97, "GGML_OP_COUNT has changed - update RPC_PROTO_PATCH_VERSION");
static_assert(GGML_OP_COUNT == 98, "GGML_OP_COUNT has changed - update RPC_PROTO_PATCH_VERSION");
#endif
#define GGML_RPC_MAX_SERVERS 16

View file

@ -576,6 +576,7 @@ extern "C" {
GGML_OP_RWKV_WKV7,
GGML_OP_SOLVE_TRI,
GGML_OP_GATED_DELTA_NET,
GGML_OP_LIGHTNING_INDEXER,
GGML_OP_UNARY,
@ -2593,6 +2594,24 @@ extern "C" {
struct ggml_tensor * state,
int64_t K);
// DSA lightning indexer
//
// q: [n_embd_idx, n_head_idx, n_batch, ne3 ]
// k: [n_embd_idx, 1, n_kv, ne3 ]
// weights: [n_head_idx, n_batch, 1, ne3 ] !! prescaled !!
// mask: [n_kv, n_batch, 1, ne33] !! f16 !!
// res: [n_kv, n_batch, 1, ne3 ]
//
// broadcast:
// ne3 % ne33 == 0
//
GGML_API struct ggml_tensor * ggml_lightning_indexer(
struct ggml_context * ctx,
struct ggml_tensor * q,
struct ggml_tensor * k,
struct ggml_tensor * weights,
struct ggml_tensor * mask);
// custom operators
typedef void (*ggml_custom1_op_t)(struct ggml_tensor * dst , const struct ggml_tensor * a, int ith, int nth, void * userdata);

View file

@ -125,12 +125,13 @@ extern "C" {
// get ith C string from array with given key_id
GGML_API const char * gguf_get_arr_str (const struct gguf_context * ctx, int64_t key_id, size_t i);
GGML_API int64_t gguf_get_n_tensors (const struct gguf_context * ctx);
GGML_API int64_t gguf_find_tensor (const struct gguf_context * ctx, const char * name); // returns -1 if the tensor is not found
GGML_API size_t gguf_get_tensor_offset(const struct gguf_context * ctx, int64_t tensor_id);
GGML_API const char * gguf_get_tensor_name (const struct gguf_context * ctx, int64_t tensor_id);
GGML_API enum ggml_type gguf_get_tensor_type (const struct gguf_context * ctx, int64_t tensor_id);
GGML_API size_t gguf_get_tensor_size (const struct gguf_context * ctx, int64_t tensor_id);
GGML_API int64_t gguf_get_n_tensors (const struct gguf_context * ctx);
GGML_API int64_t gguf_find_tensor (const struct gguf_context * ctx, const char * name); // returns -1 if the tensor is not found
GGML_API size_t gguf_get_tensor_offset(const struct gguf_context * ctx, int64_t tensor_id);
GGML_API const char * gguf_get_tensor_name (const struct gguf_context * ctx, int64_t tensor_id);
GGML_API const int64_t * gguf_get_tensor_ne (const struct gguf_context * ctx, int64_t tensor_id); // returns ne, an array of GGML_MAX_DIMS elements; ne[dim] is 1 for dim >= n_dims
GGML_API enum ggml_type gguf_get_tensor_type (const struct gguf_context * ctx, int64_t tensor_id);
GGML_API size_t gguf_get_tensor_size (const struct gguf_context * ctx, int64_t tensor_id);
// removes key if it exists, returns id that the key had prior to removal (-1 if it didn't exist)
GGML_API int64_t gguf_remove_key(struct gguf_context * ctx, const char * key);