ggml-org/llama.cpp b10067

on GitHub

llama-quant : exclude i32 ffn_gate_tid2eid routing table from quantization (#25787)

DeepSeek-V4's ffn_gate_tid2eid tensor is an i32 token-id -> expert-id
index table, not weights. It was never added to the name-based
exclusion list alongside ffn_gate_inp.weight, so llama-quantize tries
to quantize it and fails since i32 cannot convert to a float type.

Fixes #25754

Signed-off-by: Yash Raj Pandey yashpn62@gmail.com