Method get_logits_ith

subprojects/llama.cpp/src/llama-context.cpp:712–751

}

float * llama_context::get_logits_ith(int32_t i) {
    int64_t j = -1;

    output_reorder();

    try {
        if (logits == nullptr) {
            throw std::runtime_error("no logits");
        }

        // TODO: use output_resolve_row()
        if (i < 0) {
            j = n_outputs + i;
            if (j < 0) {
                throw std::runtime_error(format("negative index out of range [0, %d)", n_outputs));
            }
        } else if ((size_t) i >= output_ids.size()) {
            throw std::runtime_error(format("out of range [0, %zu)", output_ids.size()));
        } else {
            j = output_ids[i];
        }

        if (j < 0) {
            throw std::runtime_error(format("batch.logits[%d] != true", i));
        }
        if (j >= n_outputs) {
            // This should not happen
            throw std::runtime_error(format("corrupt output buffer (j=%" PRId64 ", n_outputs=%d)", j, n_outputs));
        }

        return logits + j*model.vocab.n_tokens();
    } catch (const std::exception & err) {
        LLAMA_LOG_ERROR("%s: invalid logits id %d, reason: %s\n", __func__, i, err.what());
#ifndef NDEBUG
        GGML_ABORT("fatal error");
#else
        return nullptr;
#endif
    }
}

float * llama_context::get_embeddings() {
    output_reorder();