Module glm5_next_mtp 

2026-09-25: Load GLM-5.3’s MTP block, model.language_model.layers.{num_hidden_layers}, as the body of the draft proposer.

Owner: model-arch weight loader (GLM-5.3). Invariants:

• The block is one DSA mixer and one routed MoE with mhc: None, the plain-residual path of crate::glm5next_layer::Glm5NextLayer.
• Its DSA layer uses attn_layer_idx = 0 of the drafter’s own one-layer KV pool (glm5next_mtp_head), never the target’s.
• Glm5NextWeightLoader::prune_after_load keeps this layer’s tensors: is_reuploaded matches only layer indices below num_hidden_layers.

Structs

Glm5NextMtpModule

2026-09-25: The MTP block plus the four tensors around it.

Functions

load_glm5next_mtp_module

2026-09-25: Build the MTP block, or None when the checkpoint has no layers.{num_hidden_layers}.