LLM inference in C/C++
C++ ggml
common : fix draft-mtp with embeddings (#26352, #27299) (#27400)
Shahir BIn Zulfiker2c6b141efb3b
diff --git a/common/speculative.cpp b/common/speculative.cppindex 89e9b2782c..8461e4107d 100644--- a/common/speculative.cpp+++ b/common/speculative.cpp@@ -2322,6 +2322,9 @@ common_params common_base_params_to_speculative(const common_params & params) {const auto & params_spec = params.speculative.draft;common_params result = params;+ result.embedding = false;+ result.pooling_type = LLAMA_POOLING_TYPE_UNSPECIFIED;+if (has_draft) {result.devices = params_spec.devices;result.model = params_spec.mparams;