FasterDecoding / Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
https://sites.google.com/view/medusa-llm
Apache License 2.0
2.28k stars 155 forks source link

AttributeError: 'LlamaForCausalLM' object has no attribute 'medusa_head' #60

Closed blwaji closed 9 months ago

blwaji commented 1 year ago

Snipaste_2023-11-01_11-00-21

leeyeehoo commented 10 months ago

Did you fix it? Sorry for the late reply :)

ctlllll commented 9 months ago

This thread seems to be quiet for a while. Let me close it for now, and feel free to reopen it :)