Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-11 07:19:03 +02:00
Code Issues Packages Projects Releases Wiki Activity

Don't reuse memory for output views.

Browse Source
This commit is contained in:
Gaurav Garg
2026-07-06 17:28:14 +05:30
parent f1f008b2ee
commit 813c39b225
5 changed files with 74 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+2 -1
View File
@@ -3882,7 +3882,8 @@ private:
// speculative decoding - main model sample and accept
iterate(slots, [&](server_slot & slot) {
if (slot.state != SLOT_STATE_GENERATING || !slot.can_speculate() || slot.spec_draft.empty()) {
if (slot.state != SLOT_STATE_GENERATING || !slot.can_speculate() ||
slot.spec_draft.empty() || slot.spec_i_batch.empty()) {
return;
}