CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Fix wrong bool condition for split equal in hybrid cache

Browse Source 
Branch: HybridRecurrentCache

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
This commit is contained in:
Gabe Goodhart
2025-05-28 11:02:54 -06:00
parent 423c89401d
commit 6c6ec0003a
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-kv-cache-hybrid-recurrent.cpp
View File

@@ -96,7 +96,7 @@ llama_pos llama_kv_cache_hybrid_recurrent::seq_pos_max(llama_seq_id seq_id) cons
llama_memory_state_ptr llama_kv_cache_hybrid_recurrent::init_batch(const llama_batch & batch, uint32_t n_ubatch, bool embd_pooled, bool logits_all) {
// since this includes a recurrent cache, we cannot use split_simple
auto sbatch = llama_sbatch(batch, hparams.n_embd, true, logits_all);
auto sbatch = llama_sbatch(batch, hparams.n_embd, false, logits_all);
// follow the recurrent pattern for creating the ubatch splits
std::vector<llama_ubatch> ubatches;