sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-13 12:34:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

cont : process images throught the draft context

Browse Source
This commit is contained in:
Georgi Gerganov
2026-05-07 21:34:29 +03:00
parent ae6703fa89
commit 7e118cdce0
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tools/server/server-context.cpp
View File

@@ -2732,6 +2732,13 @@ private:
continue;
}
if (ctx_drft) {
res = input_tokens.process_chunk(ctx_main, mctx, slot.prompt.n_tokens(), slot.prompt.tokens.pos_next(), slot.id, n_tokens_out);
if (res != 0) {
GGML_ABORT("failed to process multi-modal data on draft context\n");
}
}
slot.n_prompt_tokens_processed += n_tokens_out;
// add the image chunk to cache