Skip to content

Issues: predibase/lorax

Project Roadmap
#57 opened Nov 22, 2023 by tgaddair
Open 33
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
121 Open 116 Closed
121 Open 116 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

Always consider base model (no adapter) to be active enhancement New feature or request
#8 opened Nov 10, 2023 by tgaddair updated Nov 10, 2023
Extend adapters to support MLP head for embeddings, classification enhancement New feature or request
#10 opened Nov 10, 2023 by tgaddair updated Nov 10, 2023
3
Panic when adapter cannot be loaded bug Something isn't working
#14 opened Nov 12, 2023 by tgaddair updated Nov 12, 2023
4 tasks
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 updated Nov 29, 2023
2
getting error during inference "Unsupported head size: 32" bug Something isn't working
#86 opened Nov 30, 2023 by abhijithnair1 updated Nov 30, 2023
2 of 4 tasks
2
Question regarding Punica integeration question Further information is requested
#107 opened Dec 6, 2023 by psych0v0yager updated Dec 6, 2023
4
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 updated Dec 8, 2023
2 of 4 tasks
3
Some error records and questions question Further information is requested
#115 opened Dec 8, 2023 by KrisWongz updated Dec 12, 2023
1 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 updated Dec 19, 2023
Extend testing enhancement New feature or request good first issue Good for newcomers
#148 opened Dec 22, 2023 by flozi00 updated Dec 22, 2023
Does lorax currently support GPT2 finetuned adapters? enhancement New feature or request
#84 opened Nov 30, 2023 by abhijithnair1 updated Jan 2, 2024
2 of 4 tasks
19
Second GPU is not found when running --sharded true question Further information is requested
#150 opened Dec 24, 2023 by psych0v0yager updated Jan 3, 2024
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 updated Jan 9, 2024
8
vision language model support enhancement New feature or request
#179 opened Jan 11, 2024 by 7uk3y updated Jan 12, 2024
2
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 updated Jan 15, 2024
2 of 4 tasks
5
LongLM enhancement New feature or request
#182 opened Jan 15, 2024 by flozi00 updated Jan 15, 2024
1
@flozi00
1
marlin enhancement New feature or request
#188 opened Jan 17, 2024 by flozi00 updated Jan 17, 2024
1
1
Make Lorax Easier for New Users enhancement New feature or request
#185 opened Jan 16, 2024 by AdithyanI updated Jan 17, 2024
1
Add per-adapter metrics to /metrics endpoint enhancement New feature or request good first issue Good for newcomers
#203 opened Jan 23, 2024 by tgaddair updated Jan 23, 2024
Support self-trained model question Further information is requested
#208 opened Jan 25, 2024 by yangelaboy updated Jan 29, 2024
2 tasks
2
Mixtral nf4 performance 2x slower than expected question Further information is requested
#211 opened Jan 29, 2024 by timohear updated Jan 31, 2024
2 of 4 tasks
2
S3 download issues bug Something isn't working
#210 opened Jan 28, 2024 by joaopcm1996 updated Feb 1, 2024
2 of 4 tasks
2
FlashInfer integration + cascade inference (prefix caching) enhancement New feature or request
#222 opened Feb 5, 2024 by tgaddair updated Feb 7, 2024
1
Latency increase when run on multi-GPU question Further information is requested
#116 opened Dec 8, 2023 by prd-tuong-nguyen updated Feb 13, 2024
2 of 4 tasks
5
sync.sh script fails for some models (Llama-2-70b being one of them)
#238 opened Feb 12, 2024 by noyoshi updated Feb 15, 2024
4 tasks
@magdyksaleh
ProTip! Adding no:label will show everything without a label.