Skip to content

Issues: turboderp-org/exllamav2

Beta
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

123 Open 424 Closed
123 Open 424 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

[BUG] Fail to run on Pascal GPUs such as GTX 1080 ti bug Something isn't working
#786 opened May 5, 2025 by Neko-Box-Coder
3 tasks done
1
[BUG] Runtime error when trying to load Qwen3 32B bug Something isn't working
#784 opened Apr 30, 2025 by umar-mq
3 tasks done
8
[REQUEST] Qwen3 Architecture Support
#781 opened Apr 29, 2025 by Thireus
3 tasks done
20
[BUG] Blue Screen MEMORY_MANAGEMENT Error when trying to quantize Gemma3. bug Something isn't working
#780 opened Apr 28, 2025 by Nrgte
3 tasks done
1
[BUG] Sampler crashes with some vocabulary sizes? bug Something isn't working
#778 opened Apr 26, 2025 by hidoba
3 tasks done
1
[BUG]gemma 3 27b exl2 loops nonsense afterwards 2-3 correct paragraphs bug Something isn't working
#777 opened Apr 26, 2025 by ciprianveg
3 tasks done
9
[BUG] GLM-4-32B-0414 only produces gibberish bug Something isn't working
#772 opened Apr 23, 2025 by Kliffcom
3 tasks done
1
rag pdf bug Something isn't working
#767 opened Apr 10, 2025 by werruww
3 tasks done
4
[BUG]Exllamav2 repeats itself in the answer bug Something isn't working
#764 opened Apr 1, 2025 by manitadayon
3 tasks done
2
convert.py exits with a "ValueError: ## Could not find lm_head.* in model" error bug Something isn't working
#763 opened Mar 30, 2025 by CyntexMore
3 tasks done
1
[REQUEST]space HuggingFace
#762 opened Mar 25, 2025 by kim90000
3 tasks done
2
qwq32b run good in colab t4 bug Something isn't working
#761 opened Mar 24, 2025 by kim90000
3 tasks done
11
[BUG] Windows 11 Tensor Parallelism slow bug Something isn't working
#760 opened Mar 23, 2025 by frenzybiscuit
3 tasks done
2
[BUG] 0.2.7 had smaller quant sizes bug Something isn't working
#759 opened Mar 23, 2025 by frenzybiscuit
3 tasks done
7
[BUG] Cant convert model Qwen2.5-VL-7B-Instruct bug Something isn't working
#757 opened Mar 21, 2025 by MadMenHitBooker
3 tasks done
4
[REQUEST] required VRAM
#754 opened Mar 18, 2025 by kim90000
3 tasks done
18
[BUG] Loss in Accuracy with Paged=False with Qwen2.5_VL Vision Models on Linux bug Something isn't working
#753 opened Mar 18, 2025 by RaahimSiddiqi
3 tasks done
[BUG] Bug in attention mechanism when Paged=False for Qwen2.5_VL Models bug Something isn't working
#752 opened Mar 18, 2025 by RaahimSiddiqi
3 tasks done
2
[REQUEST] command-A?
#750 opened Mar 15, 2025 by Ph0rk0z
3 tasks done
3
[REQUEST] Please add support for Gemma3.
#749 opened Mar 12, 2025 by emzaedu
37
[REQUEST] It is very difficult to service exlamav2 using RestfullAPI.
#748 opened Mar 12, 2025 by nalgae
2
[REQUEST]Support for the New Aya-Vision32b models
#746 opened Mar 9, 2025 by GoudaCouda
3 tasks done
2
[BUG] Qwen-vl can't produce coordinates bug Something isn't working
#740 opened Feb 22, 2025 by Tedy50
3 tasks done
1
[BUG] Significant prompt processing speed difference when using Tensor Parallelism bug Something isn't working
#734 opened Feb 16, 2025 by ThomasBaruzier
3 tasks done
9
[BUG] When trying inference with Qwen2.5-VL-72B with Qwen2.5-VL-7B as a draft model, I get "IndexError: index out of range in self" (both models have identical vocab.json) bug Something isn't working
#733 opened Feb 6, 2025 by Lissanro
3 tasks done
5
ProTip! Exclude everything labeled bug with -label:bug.