The official source reports this update: b10760: mtmd: Fix Qwen3-tts-0.6b. mtmd: Fix Qwen3-tts-0.6b ( #28231 ) 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.
Canonical AI event
Qwen3-tts-0.6b code predictor now uses F32 for ffn_down.
The Qwen3-tts-0.6b update prevents overflow in the code predictor's layer 2 FFN intermediate.
3 Sept 20261 verified claims1 sources2 observations
This official update documents a development concerning b10760: mtmd: Fix Qwen3-tts-0.6b. Its practical significance depends on the scope and evidence stated by the source.
Read the official source update and verify its stated scope, evidence and timing before acting on it.
Connected knowledge
Entities affected by this event
Evidence trail
Sources behind the event
Editorial presentation
Open story