Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-11 04:56:56 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix server_output_limits

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-18 20:26:53 +02:00
parent 2072dfae41
commit 14cc550c70
6 changed files with 14 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+5 -2
View File
@@ -42,8 +42,11 @@ constexpr int HTTP_POLLING_SECONDS = 1;
static common_speculative_output_limits server_output_limits(const common_params & params) {
if (!params.mmproj.path.empty()) {
// gen-audio (TTS) capability isn't known until the mmproj loads, size generously
return { params.n_batch, params.n_batch };
const auto mcaps = mtmd_get_cap_from_file(params.mmproj.path.c_str());
if (mcaps.gen_audio) {
// some TTS models decode with embeddings output for the whole batch
return { params.n_batch, params.n_batch };
}
}
if (params.embedding ||