Commit 9df0b73c7 for llama.cpp

commit 9df0b73c707900b7277a46b5ae52ff7e7e567d13
Author: Georgi Gerganov <ggerganov@gmail.com>
Date:   Tue Oct 20 15:58:09 2026 +0300

    model : drop the redundant precision overrides in the Kolibri-1 router (#30865)

    * model : drop the redundant precision overrides in the Kolibri-1 router

    Follow-up to the review in #30673: the router matmul works with the
    default precision, so both ggml_prec_set_* calls can go away.

    Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB)

    * cont : fix comment

    Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

    ---------

    Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

diff --git a/src/models/kolibri1.cpp b/src/models/kolibri1.cpp
index acc1dd159..2301ef272 100644
--- a/src/models/kolibri1.cpp
+++ b/src/models/kolibri1.cpp
@@ -131,11 +131,8 @@ llama_model_kolibri1::graph::graph(const llama_model & model, const llm_graph_pa
         cur = build_norm(ffn_inp, layer.ffn_norm, NULL, LLM_NORM_RMS, il);
         cb(cur, "ffn_norm", il);

-        // The router runs in f32: the selection adds the bias to the logits, the weights
-        // are the sigmoid of the unbiased logits, so the same logits feed both.
+        // The selection adds the bias to the logits, the weights are the sigmoid of the unbiased logits, so the same logits feed both.
         ggml_tensor * logits = build_lora_mm(layer.ffn_gate_inp, cur);
-        ggml_prec_set_acc(logits, GGML_PREC_F32);
-        ggml_prec_set_src(logits, GGML_PREC_F32, 1);
         cb(logits, "ffn_moe_logits", il);

         ggml_tensor * selection = ggml_add(ctx0, logits, layer.ffn_exp_probs_b);