Skip to content

Issues: AutoGPTQ/AutoGPTQ

The Path to v1.0.0
#348 opened Sep 25, 2023 by PanQiWei
Open 2
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

206 Open 209 Closed
206 Open 209 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

[FEATURE] Add marlin24 support enhancement New feature or request
#672 opened May 14, 2024 by Qubitium
[BUG] Following the quant_with_alpaca.py example but keep getting "You shouldn't move a model that is dispatched using accelerate hooks." and the model is never saved. bug Something isn't working
#670 opened May 13, 2024 by murtaza-nasir
[BUG] Cannot install from source bug Something isn't working
#669 opened May 12, 2024 by victoryeo
Target modules [] not found in the base model. Please check the target modules and try again.
#667 opened May 10, 2024 by RicardoHalak
[BUG] ROCm installation and building broken bug Something isn't working
#666 opened May 7, 2024 by xangelix
[BUG] ARM installation error bug Something isn't working
#665 opened May 7, 2024 by DavidePaglieri
[Question] Differences in quantization logic compared to AWQ enhancement New feature or request
#663 opened May 6, 2024 by wenhuach21
[BUG]safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer bug Something isn't working
#661 opened Apr 30, 2024 by chuangzhidan
Llama-3 8B Instruct quantized to 8 Bit spits out gibberish in transformers model.generate() but works fine in vLLM?
#657 opened Apr 28, 2024 by davidgxue
5
[DEPRECATION] Discussion on Fused attention and QiGEN
#655 opened Apr 27, 2024 by Qubitium
4
[FEATURE] Backport vllm expanded Marlin kernel to autogptq.
#653 opened Apr 27, 2024 by Qubitium
1
[PR Ready for Review] [FEATURE] Extend Support for Phi-3 enhancement New feature or request
#652 opened Apr 27, 2024 by davidgxue
1
Why LLaMA3-8B after GPTQ test in wikitext2 so bad?
#650 opened Apr 26, 2024 by lyx-111111
8
What magnitude of avg loss indicates a relatively good result for a quantization model
#649 opened Apr 26, 2024 by ehuaa
6
Why doesn't AutoGPTQ quantize lm_head layer?
#647 opened Apr 25, 2024 by XeonKHJ
1
5
[BUG] Llama 3 8B Instruct - no_inject_fused_attention must be true or else errors out bug Something isn't working
#646 opened Apr 20, 2024 by davidgxue
8
gptq 4bit avg loss is large
#643 opened Apr 18, 2024 by moseshu
3
TypeError: forward() missing 1 required positional argument: 'hidden_states'[BUG] ? bug Something isn't working
#636 opened Apr 10, 2024 by silvacarl2
3
Error when quantizing mixtral 8x7b model. "ZeroDivisionError: float division by zero " bug Something isn't working
#634 opened Apr 7, 2024 by arceus-jia
1
[BUG] GPTQ Kernels dont work with PEFT bug Something isn't working
#633 opened Apr 5, 2024 by achew010
Error when trying to quantize the JAIS model.
#632 opened Apr 4, 2024 by Mohammad-Faris
10
[BUG] Can not save quantized model to disk: "you shouldn't move a model that is dispatched using accelerate hooks." bug Something isn't working
#630 opened Apr 3, 2024 by tattrongvu
1
[FEATURE] ADD Jamba Support enhancement New feature or request
#629 opened Apr 3, 2024 by TechxGenus
zeros remain zero?
#627 opened Mar 29, 2024 by RanchiZhao
[FEATURE] ADD Support DBRX enhancement New feature or request
#621 opened Mar 28, 2024 by Xu-Chen
1
16
ProTip! Adding no:label will show everything without a label.