ik-llama-cpp-sys 0.1.2

Low level bindings to ik_llama.cpp (ikawrakow's SOTA-quant fork)
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65

#pragma once

#include "llama-impl.h"

#include <cstdint>

struct llama_cparams {
    uint32_t n_ctx;           // context size used during inference
    uint32_t n_batch;
    uint32_t n_ubatch;
    uint32_t n_seq_max;
    uint32_t n_threads;       // number of threads to use for generation
    uint32_t n_threads_batch; // number of threads to use for batch processing

    std::vector<std::string> devices;
    std::vector<std::string> devices_draft;

    float rope_freq_base;
    float rope_freq_scale;

    uint32_t n_ctx_orig_yarn;
    // These hyperparameters are not exposed in GGUF, because all
    // existing YaRN models use the same values for them.
    float yarn_ext_factor;
    float yarn_attn_factor;
    float yarn_beta_fast;
    float yarn_beta_slow;
    float defrag_thold;

    bool embeddings;
    bool causal_attn;
    bool offload_kqv;
    bool flash_attn;
    int  mla_attn;
    int  attn_max_batch;
    bool fused_moe_up_gate;
    bool grouped_expert_routing;
    bool fused_up_gate;
    bool fused_mmad;
    bool rope_cache;
    bool graph_reuse;
    bool prefetch_experts;
    bool k_cache_hadamard;
    bool v_cache_hadamard;
    bool dsa_indexer_hadamard = true; // apply Walsh-Hadamard rotation to DSA indexer q/k (precision)
    bool dsa = false;                 // enable GLM DSA sparse attention (off by default; opt-in via --dsa)
    bool fused_idx_topk = false;      // enable the fused indexer topk op (off by default; opt-in via -fidx or --fused-indexer-topk)
    int  dsa_top_k = -1;              // DSA top-k override (<0 => use the model's configured indexer_top_k)
    bool split_mode_graph_scheduling;
    //bool split_mode_f16;
    bool scheduler_async;
    int  min_experts;
    float thresh_experts;
    bool mtp;
    int  worst_graph_tokens;

    enum ggml_type reduce_type;
    enum ggml_type graph_attn_precision;
    enum llama_pooling_type pooling_type;
    enum llama_mtp_op_type mtp_op_type;

    ggml_backend_sched_eval_callback cb_eval;
    void * cb_eval_user_data;
    void * cuda_params;
};