CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

batch : rework llama_batch_allocr (#14153)

Browse Source 
* batch : rework llama_batch_allocr

ggml-ci

* cont : move validation inside class

ggml-ci

* cont : move output counting to class

ggml-ci

* cont : minor

ggml-ci

* batch : add TODOs

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-13 13:47:55 +03:00
committed by GitHub
parent b7cc7745e3
commit 60c666347b
7 changed files with 162 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llama-kv-cache-unified.cpp
View File

@@ -674,6 +674,7 @@ void llama_kv_cache_unified::apply_ubatch(uint32_t head_cur, const llama_ubatch
cells.pos_set(head_cur + idx, ubatch.pos[idx]);
// TODO: fix indexing [UBATCH_IDX]
for (int32_t i = 0; i < ubatch.n_seq_id[s]; i++) {
cells.seq_add(head_cur + idx, ubatch.seq_id[s][i]);
}