// contains information about which cell moves where: // - cell i moves to ids[i] // - if ids[i] == i || ids[i] == ids.size(), then cell i is not moved
std::vector<uint32_t> ids;
};
// for each ubatch, create a slot_info that contains information about where the ubatch should be inserted in the // KV cells. for example, cell indices for each token, such that: token[i] -> goes to cells[idxs[i]] struct slot_info { // data for ggml_set_rows
using idx_vec_t = std::vector<uint32_t>;
// number of streams: ns = s1 - s0 + 1
llama_seq_id s0;
llama_seq_id s1;
// get views of the current state of the cache
ggml_tensor * get_k(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const;
ggml_tensor * get_v(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const;
// store k_cur and v_cur in the cache based on the provided head location
ggml_tensor * cpy_k(ggml_context * ctx, ggml_tensor * k_cur, ggml_tensor * k_idxs, int32_t il, const slot_info & sinfo) const;
ggml_tensor * cpy_v(ggml_context * ctx, ggml_tensor * v_cur, ggml_tensor * v_idxs, int32_t il, const slot_info & sinfo) const;
// // preparation API //
// find places for the provided ubatches in the cache, returns the slot infos // return empty vector on failure
slot_info_vec_t prepare(const std::vector<llama_ubatch> & ubatches);
// find a slot of kv cells that can hold the ubatch // if cont == true, then the slot must be continuous // return empty slot_info on failure
slot_info find_slot(const llama_ubatch & ubatch, bool cont) const;
// emplace the ubatch context into slot: [sinfo.idxs[0...ubatch.n_tokens - 1]] void apply_ubatch(const slot_info & sinfo, const llama_ubatch & ubatch);
// the current index from where we start searching for a free slot in the ring buffer of KV cells (see find_slot()) // note: this is not part of the KV state and it's only used to speed-up the find_slot() method
std::vector<uint32_t> v_heads;
std::vector<llama_kv_cells_unified> v_cells;
// maps from a sequence id to a stream id
std::vector<uint32_t> seq_to_stream;
// pending stream copies that will be applied during the next update
stream_copy_info sc_info;
std::vector<kv_layer> layers;
// model layer id -> KV cache layer id
std::unordered_map<int32_t, int32_t> map_layer_ids;
// return non-empty vector if cells have been moved
defrag_info defrag_prepare(int32_t n_max_nodes) const;
class llama_kv_cache_unified_context : public llama_memory_context_i {
public: // some shorthands
using slot_info_vec_t = llama_kv_cache_unified::slot_info_vec_t;
using defrag_info = llama_kv_cache_unified::defrag_info;
using stream_copy_info = llama_kv_cache_unified::stream_copy_info;
// used for errors
llama_kv_cache_unified_context(llama_memory_status status);
// used to create a full-cache context
llama_kv_cache_unified_context(
llama_kv_cache_unified * kv);
// used to create an update context
llama_kv_cache_unified_context(
llama_kv_cache_unified * kv,
llama_context * lctx, bool do_shift,
defrag_info dinfo,
stream_copy_info sc_info);
// used to create a batch procesing context from a batch
llama_kv_cache_unified_context(
llama_kv_cache_unified * kv,
slot_info_vec_t sinfos,
std::vector<llama_ubatch> ubatches);
// get views of the current state of the cache
ggml_tensor * get_k(ggml_context * ctx, int32_t il) const;
ggml_tensor * get_v(ggml_context * ctx, int32_t il) const;
// store k_cur and v_cur in the cache based on the provided head location
ggml_tensor * cpy_k(ggml_context * ctx, ggml_tensor * k_cur, ggml_tensor * k_idxs, int32_t il) const;
ggml_tensor * cpy_v(ggml_context * ctx, ggml_tensor * v_cur, ggml_tensor * v_idxs, int32_t il) const;
// the index of the cur ubatch to process
size_t i_cur = 0;
slot_info_vec_t sinfos;
std::vector<llama_ubatch> ubatches;
// // data needed for building the compute graph for the current ubatch: //
// a heuristic, to avoid attending the full cache if it is not yet utilized // as the cache gets filled, the benefit from this heuristic disappears
int32_t n_kv;
};
Messung V0.5 in Prozent
¤ Dauer der Verarbeitung: 0.12 Sekunden
(vorverarbeitet am 2026-08-25)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.