sleepy/llama.cpp
1
0
Fork 0
Code Issues 9 Pull Requests Actions 102 Packages Projects Releases Wiki Activity

tests: enable kv_unified to prevent cuda oom error on rtx 2060 (#20645)

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2026-03-18 17:40:22 +08:00
committed by GitHub
parent 7ab321d40d
commit fe00a84b4b
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-sampler.cpp
+1
View File
@@ -89,6 +89,7 @@ struct test_context {
cparams.n_batch = 512; cparams.n_batch = 512;
cparams.samplers = configs.data(); cparams.samplers = configs.data();
cparams.n_samplers = configs.size(); cparams.n_samplers = configs.size();
cparams.kv_unified = true;
// If n_seq_max is not specified, calculate it from configs // If n_seq_max is not specified, calculate it from configs
if (n_seq_max < 0) { if (n_seq_max < 0) {