Skip to content

Issues: predibase/lorax

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

Clear current search query, filters, and sorts
142 Open 120 Closed
142 Open 120 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

Some error records and questions question Further information is requested
#115 opened Dec 8, 2023 by KrisWongz
1 of 4 tasks
5
Extend adapters to support MLP head for embeddings, classification enhancement New feature or request
#10 opened Nov 10, 2023 by tgaddair
3
Add support for additional custom models enhancement New feature or request
#12 opened Nov 10, 2023 by tgaddair
7 tasks
1
Panic when adapter cannot be loaded bug Something isn't working
#14 opened Nov 12, 2023 by tgaddair
4 tasks
Project Roadmap enhancement New feature or request
#57 opened Nov 22, 2023 by tgaddair
16 of 36 tasks
35
Use special tokens specific to the fine-tuned adapter during decoding enhancement New feature or request
#71 opened Nov 27, 2023 by tgaddair
1
Return number of input tokens when details=True enhancement New feature or request good first issue Good for newcomers
#83 opened Nov 29, 2023 by tgaddair
1
Does lorax currently support GPT2 finetuned adapters? enhancement New feature or request
#84 opened Nov 30, 2023 by abhijithnair1
2 of 4 tasks
19
getting error during inference "Unsupported head size: 32" bug Something isn't working
#86 opened Nov 30, 2023 by abhijithnair1
2 of 4 tasks
2
how does this differ from s-Lora? question Further information is requested
#90 opened Nov 30, 2023 by priyankat99
9
How to use --master-addr <MASTER_ADDR>|--master-port <MASTER_PORT>? question Further information is requested
#99 opened Dec 4, 2023 by prd-tuong-nguyen
2 of 4 tasks
3
Is there any plan to support dynamic lora for qwen/chatglm models? enhancement New feature or request
#101 opened Dec 5, 2023 by KrisWongz
21
Fuse allgather requests across adapters and q, k, v to reduce small network requests enhancement New feature or request
#6 opened Nov 10, 2023 by tgaddair
2
Question regarding Punica integeration question Further information is requested
#107 opened Dec 6, 2023 by psych0v0yager
4
Latency increase when run on multi-GPU question Further information is requested
#116 opened Dec 8, 2023 by prd-tuong-nguyen
2 of 4 tasks
5
Add RoPE scaling CLI args enhancement New feature or request good first issue Good for newcomers
#142 opened Dec 19, 2023 by tgaddair
Extend testing enhancement New feature or request good first issue Good for newcomers
#148 opened Dec 22, 2023 by flozi00
Second GPU is not found when running --sharded true question Further information is requested
#150 opened Dec 24, 2023 by psych0v0yager
2 of 4 tasks
@tgaddair
6
Support custom tokenizer when loading a local model bug Something isn't working
#151 opened Dec 25, 2023 by yinjiaoyuan
8
Fuse q,k,v LoRAs enhancement New feature or request
#158 opened Jan 4, 2024 by tgaddair
@tgaddair
4
Support multiple ranks per SGMV op enhancement New feature or request
#160 opened Jan 4, 2024 by tgaddair
@tgaddair
ValueError: Adapter '/data/llama2-lora' is not compatible with model '/data/Llama-2-7b-chat-hf'. Use --model-id '/new-model/llama2-7b/Llama-2-7b-chat-hf' instead. question Further information is requested
#172 opened Jan 10, 2024 by Senna1960321
2 of 4 tasks
5
vision language model support enhancement New feature or request
#179 opened Jan 11, 2024 by 7uk3y
2
Skip the download process from lorax-launcher if model weights already on local disk enhancement New feature or request
#180 opened Jan 12, 2024 by tgaddair
@noyoshi
1
return_k_alternatives param causing validation error
#764 opened Mar 6, 2025 by mrcchef
4 tasks
1
ProTip! Find all open issues with in progress development work with linked:pr.