Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-13 18:28:51 +02:00
Code Issues Packages Projects Releases Wiki Activity

merge but voxtral not working

Browse Source
This commit is contained in:
Concedo
2025-07-28 22:08:05 +08:00
parent 21b7d0a899 00fa15fedc
commit b8425f5a9c
23 changed files with 1040 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+2 -2
View File
@@ -298,7 +298,7 @@ llama_context::llama_context(
cross.v_embd.clear();
// reserve pp graph first so that buffers are only allocated once
// reserve pp (prompt processing) graph first so that buffers are only allocated once
{
auto * gf = graph_reserve(n_tokens, n_seqs, n_tokens, mctx.get());
if (!gf) {
@@ -309,7 +309,7 @@ llama_context::llama_context(
n_nodes_pp = ggml_graph_n_nodes(gf);
}
// reserve with tg graph to get the number of splits and nodes
// reserve with tg (token generation) graph to get the number of splits and nodes
{
auto * gf = graph_reserve(n_seqs, n_seqs, n_seqs, mctx.get());
if (!gf) {