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: Remove logits_all after rebase

Browse Source 
Branch: HybridRecurrentCache

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
This commit is contained in:
Gabe Goodhart
2025-06-12 14:00:53 -06:00
parent d8c929ff5d
commit 1510016ea4
2 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-kv-cache-hybrid-recurrent.cpp
View File

@@ -56,10 +56,10 @@ llama_kv_cache_hybrid_recurrent::llama_kv_cache_hybrid_recurrent(
n_seq_max
)) {}
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) {
llama_memory_state_ptr llama_kv_cache_hybrid_recurrent::init_batch(const llama_batch & batch, uint32_t n_ubatch, bool embd_pooled) {
// since this includes a recurrent cache, we cannot use split_simple
auto sbatch = llama_sbatch(batch, hparams.n_embd, false, logits_all);
auto sbatch = llama_sbatch(batch, hparams.n_embd, false);
// follow the recurrent pattern for creating the ubatch splits
std::vector<llama_ubatch> ubatches;