CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : add support for qwen3 reranker (#15824)

Browse Source
This commit is contained in:
Douglas Hanley
2025-09-25 03:53:09 -05:00
committed by GitHub
parent dfcd53f7ec
commit b5bd037832
9 changed files with 166 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tools/server/server.cpp
View File

@@ -5093,21 +5093,15 @@ int main(int argc, char ** argv) {
return;
}
std::vector<server_tokens> tokenized_queries = tokenize_input_prompts(ctx_server.vocab, ctx_server.mctx, query, /* add_special */ false, true);
if (tokenized_queries.size() != 1) {
res_error(res, format_error_response("\"query\" must contain only a single prompt", ERROR_TYPE_INVALID_REQUEST));
}
// create and queue the task
json responses = json::array();
bool error = false;
std::unordered_set<int> task_ids;
{
std::vector<server_task> tasks;
auto tokenized_docs = tokenize_input_prompts(ctx_server.vocab, ctx_server.mctx, documents, /* add_special */ false, true);
tasks.reserve(tokenized_docs.size());
for (size_t i = 0; i < tokenized_docs.size(); i++) {
auto tmp = format_rerank(ctx_server.vocab, tokenized_queries[0], tokenized_docs[i]);
tasks.reserve(documents.size());
for (size_t i = 0; i < documents.size(); i++) {
auto tmp = format_rerank(ctx_server.model, ctx_server.vocab, ctx_server.mctx, query, documents[i]);
server_task task = server_task(SERVER_TASK_TYPE_RERANK);
task.id = ctx_server.queue_tasks.get_new_id();
task.index = i;