mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-05 17:40:46 -05:00
00f5442cc4
* ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer * ggml : remove scale parameters from lightning indexer OP, add f16 mask parameter * tests : add GGML_OP_LIGHTNING_INDEXER tests * ggml : bump RPC version * chore : check if lightning indexer input tensors are not transposed * tests : count flops instead of bandwidth in lightning indexer test * chore : add missing const * chore : whitespace * ggml : renamed variables in CPU lightning indexer implementation * ggml : fix lightning indexer mask broadcasting * tests : tests for lightning indexer mask broadcasting * chore : whitespace * llama : use GGML_OP_LIGHTNING_INDEXER in DeepSeek V3.2 and DeepSeek V4 models --------- Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
36 lines
1.2 KiB
C
36 lines
1.2 KiB
C
#pragma once
|
|
|
|
#include "ggml-backend.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define RPC_PROTO_MAJOR_VERSION 4
|
|
#define RPC_PROTO_MINOR_VERSION 0
|
|
#define RPC_PROTO_PATCH_VERSION 2
|
|
|
|
#ifdef __cplusplus
|
|
static_assert(GGML_OP_COUNT == 98, "GGML_OP_COUNT has changed - update RPC_PROTO_PATCH_VERSION");
|
|
#endif
|
|
|
|
#define GGML_RPC_MAX_SERVERS 16
|
|
|
|
// backend API
|
|
GGML_BACKEND_API ggml_backend_t ggml_backend_rpc_init(const char * endpoint, uint32_t device);
|
|
GGML_BACKEND_API bool ggml_backend_is_rpc(ggml_backend_t backend);
|
|
|
|
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint, uint32_t device);
|
|
|
|
GGML_BACKEND_API void ggml_backend_rpc_get_device_memory(const char * endpoint, uint32_t device, size_t * free, size_t * total);
|
|
|
|
GGML_BACKEND_API void ggml_backend_rpc_start_server(const char * endpoint, const char * cache_dir,
|
|
size_t n_threads, size_t n_devices, ggml_backend_dev_t * devices);
|
|
|
|
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_rpc_reg(void);
|
|
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_rpc_add_server(const char * endpoint);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|