Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 17:24:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

nits

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-14 00:47:07 +02:00
parent d809c0f3ab
commit 98e489eb6e
3 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+1 -1
View File
@@ -694,7 +694,7 @@ struct server_slot {
// caller need to update prompt.tokens after a successful call to keep track of the processing progress
// note: this is not a member of server_slot because we want to run it inside yield_to_queue
// slot is passed as const to avoid accidental modification of the slot state
// only llama_context / mtmd_context / mbatch are allowed to be used inside
// some pointers are allowed to be used, they are not used by to_json()
static int process_mtmd_chunk(const server_slot & slot, mtmd::batch_ptr & mbatch, size_t idx, size_t & n_tokens_out) {
GGML_ASSERT(slot.mctx);
const auto & mctx = slot.mctx;