Skip to content

Issues: mit-han-lab/streaming-llm

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

43 Open 41 Closed
43 Open 41 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

Could you provide the code for visualizing attention in Figure 2, or help us identify if there are any issues with our approach?
#90 opened Dec 11, 2024 by yuhkalhic
question about sink attention
#89 opened Nov 9, 2024 by hujiaxin0
why recompute can differ from window attention?
#88 opened Oct 11, 2024 by habaohaba
3
im confused with the PPL of sliding window with recomputation
#87 opened Oct 11, 2024 by coderwayne3025
Can you provide the code related to the visualization in the paper?
#86 opened Sep 6, 2024 by micelvrice
1
【question】Does streaming-llm focus on accelerating decoding stage? How about the prefilling stage？
#85 opened Jul 31, 2024 by Code24Man
Tokenizer issue with Transformers 4.33.0
#84 opened Jun 26, 2024 by PedemonteGiacomo
Evaluation code and dataset release inquiry
#83 opened Jun 19, 2024 by DerrickYLJ
Progressively decreasing attention windows
#80 opened May 18, 2024 by Vorlent
Using LLaVA model
#79 opened May 12, 2024 by JesseZZZZZ
why max_gen_len is needed when considering space_needed?
#78 opened Mar 29, 2024 by Mr-lonely0
How to evaluate ppl?
#77 opened Mar 13, 2024 by Jiawei-Yang
2
StreamEval
#76 opened Jan 22, 2024 by Zhangchaoran000
Support mistral-7b?
#75 opened Jan 9, 2024 by spring1915
Run with start_size=0 looks just fine
#74 opened Jan 4, 2024 by cyr0930
Error happened
#72 opened Dec 20, 2023 by ForrestPi
2
Questions about ARC datasets
#71 opened Dec 7, 2023 by Zoeyyao27
How much GPU memory needed to run example ?
#70 opened Nov 26, 2023 by fangming-he
3
Is there the way of parallel prompt ?
#69 opened Nov 21, 2023 by DavideHe
Question about attention sink arising in pretrained models
#68 opened Nov 17, 2023 by kevinli573
Request for Code and Details on Figures 2 and 7
#67 opened Nov 16, 2023 by ZhouZineng
Questions Related to the Application and Results of Attention Sinks After the Paper
#66 opened Nov 14, 2023 by dsdanielpark
Questions Regarding "Sink Tokens"
#65 opened Nov 9, 2023 by clarenceluo78
Doubts in "run_streaming_llama.py" file
#64 opened Nov 9, 2023 by Rishab9991
Results for Section 3.2 Rolling KV Cache (Without Pretraining)
#61 opened Nov 1, 2023 by timljj
1
ProTip! Updated in the last three days: updated:>2024-12-24.