tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-04 16:23:49 -04:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : use ggml_set_rows (#14285)

Browse Source 
* kv-cache : use ggml_set_rows

ggml-ci

* graph : separate k and v indices

ggml-ci

* cont : remove redundant ifs

ggml-ci

* kv-cache : improve find_slot impl

* kv-cache : bounds-check when accessing slot_info indices

* kv-cache : add comments

ggml-ci

* ggml : add TODOs for adding GGML_OP_SET_ROWS support in the backends

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-03 10:53:35 +03:00
committed by GitHub
parent 9067487c44
commit a70c8a0c4b
13 changed files with 451 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-memory-hybrid.cpp
View File

@@ -195,11 +195,11 @@ llama_memory_hybrid_context::llama_memory_hybrid_context(
llama_memory_hybrid_context::llama_memory_hybrid_context(
llama_memory_hybrid * mem,
std::vector<uint32_t> heads_attn,
slot_info_vec_t sinfos_attn,
std::vector<llama_ubatch> ubatches) :
ubatches(std::move(ubatches)),
// note: here we copy the ubatches. not sure if this is ideal
ctx_attn(new llama_kv_cache_unified_context(mem->get_mem_attn(), std::move(heads_attn), this->ubatches)),
ctx_attn(new llama_kv_cache_unified_context(mem->get_mem_attn(), std::move(sinfos_attn), this->ubatches)),
ctx_recr(new llama_memory_recurrent_context(mem->get_mem_recr(), this->ubatches)),
status(llama_memory_status_combine(ctx_attn->get_status(), ctx_recr->get_status())) {
}