Skip to content

Issues: dvmazur/mixtral-offloading

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

21 Open 7 Closed
21 Open 7 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

Hard to benchmark the operation in the repo
#39 opened Aug 29, 2024 by mynotwo
1
Mixtral Instruct tokenizer from Colab notebook doesn't work.
#38 opened Jul 8, 2024 by jmuntaner-smd
2
Support DeepSeek V2 model
#36 opened May 15, 2024 by Minami-su
Having issue loading my HQQ quantized model
#35 opened Apr 24, 2024 by BeichenHuang
How to split the model parameter safetensors file into multiple small files
#34 opened Apr 18, 2024 by YLSnowy
5
Implementation of benchmarks (C4 perplexity, Wikitext perplexity)
#33 opened Apr 14, 2024 by ChengSashankh
runtimeerror when nbit = 4 and group_size =64
#32 opened Apr 13, 2024 by Eutenacity
Can this be used for Jambo inference
#30 opened Apr 8, 2024 by freQuensy23-coder
1
a strange issue with default parameters " RuntimeError about memory"
#26 opened Mar 24, 2024 by a1564740774
Update Requirements.txt
#25 opened Feb 18, 2024 by Soumadip-Saha
Run on second GPU (torch.device("cuda:1"))
#24 opened Feb 9, 2024 by imabot2
1
4bit-3bit model produces gibberish when plugged into demo
#23 opened Feb 4, 2024 by jjblum
Run without quantization
#22 opened Jan 22, 2024 by freQuensy23-coder
9
need mixtral offload for NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
#19 opened Jan 16, 2024 by githubpradeep
CUDA OOM errors in wsl2
#18 opened Jan 12, 2024 by MrNova111
Is it possible to finetune this on a custom dataset?
#17 opened Jan 10, 2024 by asmith26
8
Can it run with LlamaIndex?
#16 opened Jan 10, 2024 by LeMoussel
Can it run on multi-GPU?
#15 opened Jan 8, 2024 by drdh
10
Mixtral OffLoading/GGUF/ExLlamaV2, which approach to use?
#11 opened Jan 2, 2024 by LeMoussel
1
Enhancing the Efficacy of MoE Offloading with Speculative Prefetching Strategies
#10 opened Jan 2, 2024 by yihong1120
1
exl2
#4 opened Dec 29, 2023 by eramax
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.