Skip to content

Issues: casper-hansen/AutoAWQ

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

164 Open 270 Closed
164 Open 270 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

Load Qwen/Qwen2-7B-Instruct-AWQ error: RuntimeError: Only Tensors created explicitly by the user (graph leaves) support the deepcopy protocol at the moment
#693 opened Jan 16, 2025 by liuzhishan
3
Failed to convert Qwen2-VL-7B-Instruct LORA model
#692 opened Jan 16, 2025 by songyang23
Same Memory (VRAM) with different batch_size, Prefill Length, Decode Length.
#691 opened Jan 15, 2025 by rayzr0123
keep getting error regarding missing positional argument 'attention_mask'
#690 opened Jan 14, 2025 by BBC-Esq
5
Multi-GPU/CPU offloading is still not working as intended
#689 opened Jan 7, 2025 by haitham-boxmind
llama3.1 quantization
#687 opened Dec 31, 2024 by sunjianxide
Deepseek
#686 opened Dec 30, 2024 by ehartford
2
Support AutoAWQForSequenceClassification ？
#685 opened Dec 27, 2024 by ShelterWFF
Any chance at supporting Nemotron?
#684 opened Dec 19, 2024 by ambroser53
prepare_inputs_for_generation and position_embeddings
#683 opened Dec 17, 2024 by ambroser53
Please support cohere2 model
#682 opened Dec 17, 2024 by Orion-zhen
How to use multiple GPU nodes during quantization
#679 opened Dec 12, 2024 by ghntd
1
How to convert AWQ matmul to onnxruntime MatmulNBits
#677 opened Dec 9, 2024 by fuyao2024
can I quantize a model to 8bit model using autoawq?
#675 opened Dec 8, 2024 by cute149q
Question: Error when substituting the quantized matrix multiplication operator.
#670 opened Dec 4, 2024 by grysgreat
2
probability tensor contains either inf, nan or element < 0
#657 opened Nov 26, 2024 by alvaropastor7
2
"llama_model_load: error loading model: check_tensor_dims: tensor 'token_embd.weight' not found" after computing AWQ scales and applying them to the gguf model
#655 opened Nov 25, 2024 by Autism-al
1
how to push model to huggingface ?
#646 opened Nov 16, 2024 by new-Sunset-shimmer
2
"zero_point":False in quant_fig dict
#643 opened Nov 8, 2024 by Cornelii
1
Does AutoAWQ support to quantize GLM-4-9B-Chat and ChatGLM3-6B two models?
#642 opened Nov 7, 2024 by shawn9977
DeepSeek-Coder-V2-Lite-Instruct Error!
#640 opened Oct 30, 2024 by tohnee
1
Mixtral training
#639 opened Oct 25, 2024 by ChristianPala
After using autoawq to quantify the model, an error occurs when inferring the model
#636 opened Oct 21, 2024 by xuanzhangyang
ImportError: /root/anaconda3/envs/test2/lib/python3.10/site-packages/awq_inference_engine.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda9SetDeviceEi
#635 opened Oct 20, 2024 by Jackson-cj
1
[Feature Request]. Support Reward Model
#634 opened Oct 20, 2024 by liziniu
ProTip! Follow long discussions with comments:>50.