Files
llama.cpp/ggml/include/ggml-rpc.h
T
gianni-corandJohannes Gäßler ad50351f50 ggml : add SIGMOID backward pass (#32126)
* ggml : add SIGMOID backward pass

Sigmoid is used in Qwen3.5 hybrid models and had no backward pass.
Bump RPC protocol patch version for the new op.

Signed-off-by: gianni-cor <gianfranco.cordella@tether.io>

* replace assert with ggml_assert

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* ggml : keep sigmoid backward checks in release builds

Assisted-by: Codex

* ggml : preserve existing operation IDs when adding SIGMOID_BACK

Assisted-by: Codex

---------

Signed-off-by: gianni-cor <gianfranco.cordella@tether.io>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2026-11-22 13:33:13 +02:00

41 lines
1.1 KiB
C

#pragma once
#include "ggml-backend.h"
#ifdef __cplusplus
extern "C" {
#endif
#define RPC_PROTO_MAJOR_VERSION 10
#define RPC_PROTO_MINOR_VERSION 0
#define RPC_PROTO_PATCH_VERSION 2
#ifdef __cplusplus
static_assert(GGML_OP_COUNT == 101, "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