Skip to content

Issues: FMInference/DejaVu

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

26 Open 9 Closed
26 Open 9 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

lm_head.weight in convert_opt_checkpoint.py
#36 opened Oct 31, 2024 by quaternior
How to calculate Activated Neurons
#34 opened Sep 20, 2024 by LiuJinzhe-Keepgoing
No such file ./trace_json/xxxxx
#33 opened Sep 4, 2024 by MathsCode
How to test the sparsity of the model？
#32 opened Aug 21, 2024 by lw20191012
2
Training of predictors based on MOE model
#31 opened Jul 23, 2024 by mailonghua
Question about downsteam tasks accuracy
#30 opened Jul 10, 2024 by W-215
the issue of parameter settings
#29 opened Jun 7, 2024 by W-215
How to run on a single GPU?
#28 opened Apr 17, 2024 by xbzjsj
7
PyTorch 1.12 and flash-attn==0.2.8 are not compatible.
#27 opened Apr 10, 2024 by heheda12345
the code about collect activations while inferencing
#25 opened Apr 9, 2024 by mli-tian
1
How to run the code with smaller ckpt like opt-6.7B
#24 opened Apr 6, 2024 by czq693497091
14
A question about attention block sparsity
#23 opened Mar 22, 2024 by imh966
Miss csrc folder when building docker images
#19 opened Feb 2, 2024 by Mi5sssss
3
Does anyone know if this work is implemented on llama?
#18 opened Jan 25, 2024 by wyxscir
5
Please give a instruction to run Hardware-efficient Implementation dejaVu model inferenc,I Can't find the moudle src.models.gpt_sparse
#17 opened Jan 23, 2024 by wangzhenyu32
Question about OPT-30B
#16 opened Jan 4, 2024 by Jimskns
Missing full.pt when running latency benchmark
#15 opened Dec 23, 2023 by PaulWang0513
LLama 2 compatability
#14 opened Nov 6, 2023 by yomanFX
Some questions about implementation details
#13 opened Oct 30, 2023 by SUDA-HLT-ywfang
3
Failed to collect training data for sparsity predictor
#11 opened Oct 7, 2023 by PaulWang0513
9
Compare the sparse model on downstream tasks
#10 opened Oct 2, 2023 by iidsample
2
Missing lm_eval harness for downstream task prediction
#9 opened Oct 2, 2023 by iidsample
Inconsisten File Names
#8 opened Oct 2, 2023 by iidsample
Missing Argument and Filtering
#7 opened Sep 30, 2023 by iidsample
Training MLP layer Issue
#6 opened Sep 30, 2023 by iidsample
1
ProTip! no:milestone will show everything without a milestone.