* llama: create new fused op for QSA scoring * enroll glm5.3-next too * tests : initialize the remaining tensors in test_kpool_mask The harness sentinels were left uninitialized, so leftover memory could read as NaN and fail the NaN check. * ggml: generalize the k-pool mask op into ggml_top_k_mask The k-pool mask op only covered the pooled QSA selection of qwen4exp and glm5-next, while the DSA models and the DeepSeek V4 CSA build the same top-k mask by hand with fill, set_rows and add. ggml_top_k_mask(mask, top_k, score, blocks, extra) keeps the mask cells of the live picks and the extra cells, and sets the rest to -inf. Every row tensor is 4D in the layout of top_k, and the mask is broadcast to those rows, so a selection can also be made per head. score, blocks and extra are optional: without score every pick is live, without blocks a pick is a cell, and extra holds the cells a row keeps without a pick. llm_graph_context::build_fused_top_k_mask views the row tensors in the layout of kq_mask and registers the fused node. The k-pool models, the DSA attention of build_attn and the DeepSeek V4 CSA mask use it when the probe enables the op, and keep their current path on backends without it. --------- Co-authored-by: Pascal <admin@serveurperso.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 8
|
|
#define RPC_PROTO_MINOR_VERSION 0
|
|
#define RPC_PROTO_PATCH_VERSION 1
|
|
|
|
#ifdef __cplusplus
|
|
static_assert(GGML_OP_COUNT == 102, "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
|