Skip to content

Issues: FasterDecoding/Medusa

Roadmap
#3 opened Sep 12, 2023 by ctlllll
Open 15
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

41 Open 46 Closed
41 Open 46 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

How to run inference of a baseline model without medusa support?
#123 opened Sep 16, 2024 by kailashg26
About the Tree Sparsity
#122 opened Sep 13, 2024 by PineTreeWss
[Retraining] Use Liger Kernel to avoid multi-head logits materialization and scale the context length by N times
#119 opened Aug 26, 2024 by ByronHsu
1
Training code is not working
#118 opened Aug 25, 2024 by ksajan
2
Instruct data format
#117 opened Aug 13, 2024 by orhan6116
Are Medusa Heads computed in parallel or serially?
#116 opened Aug 3, 2024 by userljz
jinja2.exceptions.UndefinedError: dict object has no element 0
#115 opened Jul 30, 2024 by LLLL114
2
updated medusa models in huggingface?
#114 opened Jul 25, 2024 by hustxiayang
[ISSUE] The Pull Request at https://github.com/FasterDecoding/Medusa/pull/97 from Narsil/medusa2 needs to be rolled back.
#112 opened Jul 11, 2024 by super-ahn
Does Medusa support beam search decoding strategy?
#108 opened Jun 14, 2024 by xs229
The implementation of stage 2 with axolotl
#107 opened May 24, 2024 by boxiaowave
PPL compute
#106 opened May 23, 2024 by yuyangxie96
Containerization with Dockerfile to setup medusa
#104 opened May 16, 2024 by gangooteli
Conversation roles must alternate user/assistant/user/assistant/
#102 opened May 13, 2024 by gangooteli
[bug] fix preprocess function
#101 opened Apr 28, 2024 by xiezipeng-ML
Using Medusa with Whisper
#100 opened Apr 25, 2024 by AvivSham
5
ImportError: cannot import name 'is_flash_attn_available' from 'transformers.utils'
#98 opened Apr 12, 2024 by imneov
2
Is there a bug in gen_model_answer_baseline.py?
#96 opened Apr 10, 2024 by qspang
1
Medusa Training Loss
#95 opened Apr 7, 2024 by TomYang-TZ
5
train medusa stage-2
#94 opened Apr 6, 2024 by smartliuhw
1
mistral.json
#93 opened Apr 6, 2024 by Git-L1
which dataset should i use when training medusa heads with llama2 7b
#92 opened Apr 3, 2024 by tu2022
Cant it support chatgllm?
#91 opened Mar 26, 2024 by PeterXiaTian
HYDRA support?
#90 opened Mar 15, 2024 by arunpatala
Misleading Name LLM Name MEDUSA
#89 opened Mar 8, 2024 by Pittconnect
ProTip! Updated in the last three days: updated:>2024-10-06.