shahondin1624/llama.cpp
1
0
Fork 0
Code Issues 2 Pull Requests Actions 3 Packages Projects Releases Wiki Activity

llama: initialize pre-norm embedding mask flag (#23256)

Browse Source
This commit is contained in:
Andrei
2026-05-18 04:20:49 -07:00
committed by GitHub
parent 77e38d68f2
commit 49c21f97cd
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+3 -2
View File
@@ -64,8 +64,9 @@ llama_context::llama_context(
cparams.yarn_attn_factor = params.yarn_attn_factor >= 0.0f ? params.yarn_attn_factor : hparams.yarn_attn_factor;
cparams.yarn_beta_fast = params.yarn_beta_fast >= 0.0f ? params.yarn_beta_fast : hparams.yarn_beta_fast;
cparams.yarn_beta_slow = params.yarn_beta_slow >= 0.0f ? params.yarn_beta_slow : hparams.yarn_beta_slow;
cparams.embeddings = params.embeddings;
cparams.embeddings_pre_norm = false;
cparams.embeddings = params.embeddings;
cparams.embeddings_pre_norm = false;
cparams.embeddings_pre_norm_masked = false;
cparams.offload_kqv = params.offload_kqv;
cparams.no_perf = params.no_perf;
cparams.pooling_type = params.pooling_type;