mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-04 02:37:27 +02:00
Pascal
0f3a71be15
* mtmd: load the qwen3-tts code predictor proj_in as optional The talker and the code predictor share the hidden size on the 0.6B checkpoints, so the reference builds no small_to_mtp_projection and the conversion emits no tensor for it. The graph already falls back to identity when the weight is missing, the loader now agrees. * mtmd: keep the qwen3-tts code predictor ffn_down in F32 The code predictor carries a massive activation: its layer 2 FFN intermediate peaks around 1.5e5, well past the 65504 ceiling of F16. mul_mat casts its input to the weight type, so an F16 ffn_down turns that peak into inf, the residual follows, and the next rms_norm yields NaN. Reference forward in float32 gives 145109 against 145396 measured in the graph.