Skip to content

Issues: turboderp/exllama

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

59 Open 160 Closed
59 Open 160 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

Run on CPU without AVX2
#315 opened Apr 14, 2024 by ZanMax
3
piece id is out of range
#314 opened Apr 9, 2024 by chethanwiz
3
When will the bfloat16 type of GPTQ algorithm be supported?
#310 opened Dec 20, 2023 by Kelang-Tian
Does it support safetytensor formate?>
#309 opened Nov 28, 2023 by lucasjinreal
Error when using Beam Search
#308 opened Nov 17, 2023 by bibekyess
Occasionally RuntimeError
#307 opened Nov 16, 2023 by leegohi04517
Using Exllama backend requires all the modules to be on GPU - how?
#306 opened Nov 6, 2023 by tigerinus
1
Changing hyper-parameters after initilization without reloading weights from disk.
#299 opened Sep 28, 2023 by kmccleary3301
doesn't use CUDA_HOME?
#293 opened Sep 20, 2023 by j2l
OSError: CUDA_HOME environment variable is not set.
#291 opened Sep 17, 2023 by jamesbraza
8
CodeLLaMA + LoRA: RuntimeError: CUDA error: an illegal memory access was encountered
#290 opened Sep 15, 2023 by juanps90
3
GPU Inference from IPython
#289 opened Sep 15, 2023 by Rajmehta123
followed instructions with error
#288 opened Sep 15, 2023 by hiqsociety
2
Multi-GPU issues
#281 opened Sep 9, 2023 by nktice
9
Support for Baichuan2 models
#280 opened Sep 9, 2023 by bernardx
1
Progress on the rewrite for older cards (Like the P40)
#279 opened Sep 8, 2023 by TimyIsCool
1
remove tokens that exceed the max_seq_len
#274 opened Sep 5, 2023 by p11188536
1
Completion abruptly stopped - RuntimeError: CUDA error: an illegal memory access was encountered
#273 opened Sep 4, 2023 by Thireus
1
YaRN Support
#272 opened Sep 2, 2023 by grimulkan
8
Codelama support
#270 opened Sep 1, 2023 by ParisNeo
11
Support for AMD ROCM
#268 opened Aug 30, 2023 by yehowshuaradialrad
1
Is it possible and efficient if load layer on demand?
#267 opened Aug 30, 2023 by fahadh4ilyas
2
Speed on A100
#266 opened Aug 30, 2023 by Ber666
4
Any blogs on the project?
#264 opened Aug 30, 2023 by qizzzh
Performance issues
#263 opened Aug 29, 2023 by bryanhpchiang
3
ProTip! Mix and match filters to narrow down what you’re looking for.