CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-06 09:46:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix typos in server.cpp comments [no ci] (#16883)

Browse Source
This commit is contained in:
Daniel Bevenius
2025-10-31 09:51:26 +01:00
committed by GitHub
parent d2d931f173
commit 0f715b4e75
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tools/server/server.cpp
View File

@@ -3608,7 +3608,7 @@ struct server_context {
slot.task->params.sampling.preserved_tokens.find(token) != slot.task->params.sampling.preserved_tokens.end();
};
// frist, add sampled tokens from any ongoing sequences
// first, add sampled tokens from any ongoing sequences
for (auto & slot : slots) {
if (slot.state != SLOT_STATE_GENERATING) {
continue;
@@ -3950,7 +3950,7 @@ struct server_context {
// If using an alora, there may be uncached tokens that come
// before the invocation sequence. When this happens, the
// tokens before the invocation sequence need to be
// processed without the adpter in a separate batch, then
// processed without the adapter in a separate batch, then
// the adapter needs to be enabled for the remaining tokens.
if (lora_all_alora(slot.lora) && slot.alora_invocation_start - 1 > slot.prompt.n_tokens()) {
SLT_DBG(slot, "processing pre-alora tokens without the adapter (n_tokens = %d, alora_invocation_start = %d)\n", slot.prompt.n_tokens(), slot.alora_invocation_start);