upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-03 03:17:32 -05:00
Code Issues Packages Projects Releases Wiki Activity

add docs, imorove UX a bit

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-10-01 20:16:55 +02:00
parent d244cdcf3d
commit 93ed62dce6
8 changed files with 159 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+1 -5
View File
@@ -5324,14 +5324,10 @@ void server_routes::init_routes() {
this->post_systemone = [this](const server_http_req & req) {
auto res = create_response();
const auto & decision = ctx_server.decision;
if (decision.type == SERVER_DECISION_TYPE_NONE) {
if (decision.type == COMMON_DECISION_TYPE_NONE) {
res->error(format_error_response("This model is not a decision model", ERROR_TYPE_NOT_SUPPORTED));
return res;
}
if (decision.need_embd() && (!params.embedding || meta->pooling_type != LLAMA_POOLING_TYPE_NONE)) {
res->error(format_error_response("This decision model requires `--embedding --pooling none`", ERROR_TYPE_NOT_SUPPORTED));
return res;
}
const json body = json::parse(req.body);
const auto questions = decision.parse_questions(body);