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

132 Open 118 Closed
132 Open 118 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

Attention not working properly in FlashRobertaModel and FlashBertModel
#694 opened Nov 22, 2024 by sgiorgis
2 of 4 tasks
why prune in mergeStrategy no rescale remaining?
#685 opened Nov 19, 2024 by zhujianwei-ops
Not able to host Llama3.2-11b on Azure A100 80GB server
#679 opened Nov 13, 2024 by alokgupta1996
2 of 4 tasks
2
Cannot run a FP8 quantized model with LoraX
#671 opened Nov 11, 2024 by Aktsvigun
2 of 4 tasks
Throughput and Latency degradation with a single LoRA adapter on A100 40 GB
#670 opened Nov 8, 2024 by kaushikmitr
2 of 4 tasks
1
Multi-responses for a single inference
#665 opened Nov 5, 2024 by mrcchef
Things started failing after new commit into main
#661 opened Oct 30, 2024 by gane5hvarma
2 of 4 tasks
2
Issue: recognizing a base causal language model as an embedding model
#657 opened Oct 24, 2024 by veezbo
2 of 4 tasks
1
Unexpected response with long-context model (Phi-3)
#651 opened Oct 17, 2024 by prd-tuong-nguyen
2 of 4 tasks
Phi 3.5 vision (4B model) enhancement New feature or request
#637 opened Oct 8, 2024 by CheeseAndMeat
2 tasks done
2
Not able to run source code
#636 opened Oct 8, 2024 by nirvitarka
2 of 4 tasks
Performance issues on AWQ and Lora
#611 opened Sep 18, 2024 by dumbPy
2 of 4 tasks
Running several adapters on the same input
#606 opened Sep 15, 2024 by arnaud-secondlayer
2
seems like when max total token is so huge like 130000, and in the request if there is no max new token the response will be wrong
#601 opened Sep 11, 2024 by ejiang-eog
1 of 4 tasks
Fail to run server with prefix-caching option
#599 opened Sep 11, 2024 by prd-tuong-nguyen
2 of 4 tasks
1
The server is failing to run
#591 opened Aug 27, 2024 by u650080
1 of 4 tasks
Passing a --revision causes failure in loading tokenizer config
#563 opened Aug 1, 2024 by chiragjn
2 of 4 tasks
if LoRAX is based on punica kernels will it be able to support LoRA Adapters for Mistral NeMO 12B?
#549 opened Jul 20, 2024 by tensimixt
2
Support Lora Adapter generated from mistral-finetune
#546 opened Jul 19, 2024 by tensimixt
1
LORAX_USE_GLOBAL_HF_TOKEN is not applied at the first time of calling adapter from huggingface private hub
#541 opened Jul 16, 2024 by monologg
2 of 4 tasks
1
Stop word is included on phi-2
#537 opened Jul 11, 2024 by yunmanger1
4 tasks
RuntimeError: CUDA error: no kernel image is available for execution on the device
#535 opened Jul 3, 2024 by nethi
3 of 4 tasks
1
Adding Whisper model
#526 opened Jun 26, 2024 by Jeevi10
2 tasks done
Fails hard on CUDA error
#523 opened Jun 22, 2024 by yunmanger1
2 of 4 tasks
7
Generating garbage output
#521 opened Jun 19, 2024 by shreyansh26
2 of 4 tasks
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.