Skip to content

Issues: tloen/llama-int8

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

14 Open 3 Closed
14 Open 3 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

Does this support llama2 as well?
#21 opened Feb 16, 2024 by YaoJiayi
Producing nan Tensors
#20 opened Jun 15, 2023 by Bryan-Lavender
65B on multiple GPUs : CUDA out of memory with 4 x GPU RTX A5000 (24GB) / 96GB in total
#18 opened Mar 14, 2023 by scampion
3
LLaMA 13B works on a single RTX 4080 16GB
#17 opened Mar 13, 2023 by kcchu
1
Further detail needed - installing bitsandbytes from source
#16 opened Mar 13, 2023 by chrisbward
1
Getting error on generation in Windows
#12 opened Mar 10, 2023 by elephantpanda
4
Can 65B run on 4*32G GPU?
#11 opened Mar 8, 2023 by zhongtao93
Is it possible to save the smaller weights so it doesn't have to convert them each time?
#10 opened Mar 7, 2023 by spullara
Systematic comparison of original models to int8 inferencing
#9 opened Mar 7, 2023 by innokean
1
When a single A100 80G ,memory is about 96G,Error loading 65B
#8 opened Mar 6, 2023 by dpyneo
3
Any chance to share quantized int8 7B and 13B models?
#6 opened Mar 6, 2023 by progressionnetwork
Does 8GB able to run smallest llama model?
#5 opened Mar 6, 2023 by lucasjinreal
4
Tracking issue for Mac support
#4 opened Mar 5, 2023 by pannous
3
13B - load is successful on T4, but forward pass fails
#2 opened Mar 5, 2023 by deep-diver
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.