From: Piotr Wilkin (ilintar) <redacted>
Date: Fri, 28 Nov 2025 11:02:56 +0000 (+0100)
Subject: model : Qwen3 Next (llama/16095)
X-Git-Tag: upstream/0.9.4.395~100
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=8e7df929f6704a9da47082354ad42cbe6a75371d;p=pkg%2Fggml%2Fsources%2Fggml

model : Qwen3 Next (llama/16095)

* Qwen3 Next - cleaned up version

* Whitespaces and stuff

* Correct minor errors

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <redacted>

* 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 <redacted>

* Usual suspects

* fix my bad suggestion

---------

Co-authored-by: Sigbjørn Skjæret <redacted>
Co-authored-by: Georgi Gerganov <redacted>
---

diff --git a/src/ggml-cpu/ops.cpp b/src/ggml-cpu/ops.cpp
index d4056965..2745fc54 100644
--- a/src/ggml-cpu/ops.cpp
+++ b/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;
         }
     }