vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

some tweaks and cleanup

Browse source
This commit is contained in:
Concedo 2025-01-13 23:50:54 +08:00
parent 636beac6d2
commit e77d566268
3 changed files with 8 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama.cpp
View file

@ -11124,7 +11124,7 @@ static int llama_decode_impl(
GGML_ASSERT_CONTINUE(n_tokens_all <= cparams.n_batch);
GGML_ASSERT_CONTINUE((cparams.causal_attn || cparams.n_ubatch >= n_tokens_all) && "non-causal attention requires n_ubatch >= n_tokens");
//GGML_ASSERT_CONTINUE((cparams.causal_attn || cparams.n_ubatch >= n_tokens_all) && "non-causal attention requires n_ubatch >= n_tokens");
if (lctx.t_compute_start_us == 0) {
lctx.t_compute_start_us = ggml_time_us();