Skip to content

Issues: SafeAILab/EAGLE

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

28 Open 95 Closed
28 Open 95 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

Is the forward related to gen_ea_alpha_llama2chat.py fully implemented?
#136 opened Sep 27, 2024 by YunSeoHwan
1
VLLM does not support EAGLE Spec Decode when deploying EAGLE-Qwen2-7B-Instruct model
#135 opened Sep 25, 2024 by crownz248
How can I inference a 70B model
#134 opened Sep 23, 2024 by Siegfried-qgf
Deploy EAGLE-Qwen2 in vllm
#130 opened Sep 14, 2024 by IvanDeng0
4
LLama 3.1 8b training issue.
#129 opened Sep 5, 2024 by dhananjaybhandiwad
1
Regarding training data of EAGLE
#128 opened Sep 4, 2024 by KanghoonYoon
1
Question on quantized LLAMA3 versions for use with EAGLE
#127 opened Sep 3, 2024 by jin-eld
Batched speculation benchmarks? (incl. with compilation)
#126 opened Aug 28, 2024 by poedator
2
Training of Qwen2
#125 opened Aug 28, 2024 by jzzzf
1
what's the difference between ea_generate and eagenerate
#123 opened Aug 22, 2024 by LSC527
1
When Train the Auto-regression Head, RuntimeError: CUDA error: device-side assert triggered
#122 opened Aug 20, 2024 by liuy-2019
Can not reproduce speedup results reported in the paper.
#121 opened Aug 19, 2024 by shaonan1993
3
Some questions that arise when studying your code
#120 opened Aug 16, 2024 by bulaikexiansheng
2
Actual parameter setting for different sizes of the model?
#118 opened Aug 13, 2024 by Lucas-TY
1
What's the relationship between total token and depth
#96 opened Jul 15, 2024 by Lucas-TY
1
How to handle embedding layernorm
#91 opened Jul 9, 2024 by xiongqisong
10
Would like to see base models
#86 opened Jun 30, 2024 by rombodawg
Are you going to support Gemma-2?
#85 opened Jun 28, 2024 by jumasheff
have you guys tried other speculative draft model with eagle-2 method?
#84 opened Jun 28, 2024 by hanlinxuy
Question about past_key_value modification
#82 opened Jun 21, 2024 by baihuajun24
2
reproducing eagle on mistral-7b-v0.3-instruct
#79 opened Jun 4, 2024 by alcholiclg
6
Why does EAGLE remove the input_layernorm of llama?
#76 opened May 26, 2024 by bisunny
2
Updates on training moe eagle model?
#71 opened May 14, 2024 by cyLi-Tiger
difference between the target input_ids and original LLMs in function getkacc()
#70 opened May 7, 2024 by kafkayu
new model
#66 opened Apr 26, 2024 by shunxing12345
6
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.