unsloth

/

GLM-4.6-GGUF

like 130

Follow

Unsloth AI 10.7k

Hey,

I am running the Q2 version with llama.cpp latest version and a I get a lot of these errors. I believe these are making my model unusable. Anyone know what this is?

init: the tokens of sequence 0 in the input batch have inconsistent sequence positions:

• the last position stored in the memory module of the context (i.e. the KV cache) for sequence 0 is X = 19
• the tokens for sequence 0 in the input batch have a starting position of Y = 1098
  it is required that the sequence positions remain consecutive: Y = X + 1
  decode: failed to initialize batch
  llama_decode: failed to decode, ret = -1
  srv update_slots: Invalid input batch. i = 0, n_batch = 2048, ret = -1
  srv send_error: task id = 324160, error: Invalid input batch.

srv update_slots: all slots are idle
srv cancel_tasks: cancel task, id_task = 324163
srv update_slots: all slots are idle

Thank you!