From 43441ff58aa9e29d75fb99d288598310ea3b881d Mon Sep 17 00:00:00 2001 From: "Piotr Wilkin (ilintar)" Date: Fri, 28 Nov 2025 12:02:56 +0100 Subject: [PATCH] model : Qwen3 Next (llama/16095) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * Qwen3 Next - cleaned up version * Whitespaces and stuff * Correct minor errors * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret * Misc. fixes. * Clean up code, add missing hybrid qualifier * Did someone transpose the SOLVE_TRI result matrix? Perhaps... * Whitespace * Proper tensors for cb calls * Use llama-graph.h vertical alignment * BROKEN: chunking * Set new tensors as inputs. * Proper chunk logic * It's the circle of life... * More shenanigans for n_seq > 1 * Nail in the coffin? * Fix Windows build * Eh, one fails on Windows, the other fails on Mac... just use general capture. * quant : cleanup * model : cleanup * qwen3 : cleanup * cont : cleanup * cont : cleanup * ggml : revert change * qwen3 : cleanup * cont : cleanup * Readd cmath * qwen3 : fix typo * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret * Usual suspects * fix my bad suggestion --------- Co-authored-by: Sigbjørn Skjæret Co-authored-by: Georgi Gerganov --- ggml/src/ggml-cpu/ops.cpp | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/ggml/src/ggml-cpu/ops.cpp b/ggml/src/ggml-cpu/ops.cpp index d4056965..2745fc54 100644 --- a/ggml/src/ggml-cpu/ops.cpp +++ b/ggml/src/ggml-cpu/ops.cpp @@ -9766,7 +9766,8 @@ static void ggml_compute_forward_solve_tri_f32(const struct ggml_compute_params } const float diag = A_batch[i00 * n + i00]; - GGML_ASSERT(diag != 0.0f && "Zero diagonal in triangular matrix"); + assert(diag != 0.0f && "Zero diagonal in triangular matrix"); + X_batch[i00 * k + i01] = (B_batch[i00 * k + i01] - sum) / diag; } }