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

39 Open 103 Closed
39 Open 103 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

Question on Feature & Unshifted token in Experiments
#159 opened Nov 12, 2024 by kimjoohyungsd
Question about topk_index = topk_index.view(-1) in cnets.py
#158 opened Nov 7, 2024 by HaoWuSR
About Llama-2 7B training
#155 opened Nov 5, 2024 by sunnywyang
1
There is a problem with reproduction
#154 opened Oct 28, 2024 by skylee-01
6
How to reproduce average acceptance length?
#153 opened Oct 24, 2024 by garipovroma
1
Random Hidden and Epochs > 1
#152 opened Oct 24, 2024 by Ageliss
2
The disk space need for generating data for train.
#151 opened Oct 23, 2024 by bulaikexiansheng
1
About the acceptance rate
#147 opened Oct 16, 2024 by YunSeoHwan
2
Issue about the comparison with Lookahead
#145 opened Oct 11, 2024 by lethean1
1
Inquiry about accept length results for EAGLE-Qwen2-7B-Instruct
#143 opened Oct 9, 2024 by zhangtia16
2
DeepSeekV2
#142 opened Oct 9, 2024 by fengyang95
1
Why the bias of config in train scripts doesn't aligning at infererence?
#141 opened Oct 8, 2024 by 870572761
1
VLLM does not support EAGLE Spec Decode when deploying EAGLE-Qwen2-7B-Instruct model
#135 opened Sep 25, 2024 by crownz248
1
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
2
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
ProTip! Exclude everything labeled bug with -label:bug.