-
### Describe the bug
I am trying to use mmrazor to quantize the model, but it gives me the following error and fails -
Traceback (most recent call last):
File "tools/ptq.py", line 74, in
…
-
Hello.
One issue with CSG as opposed to voxel-based geometry is that there's essentially no upper bound on the complexity of the geometry that can be created. For example, if you create a sphere an…
-
This is taking about 2 hours with the smallest model.
I presume the issue is that my GPU cannot load a t5_XXL model into memory. According to the Huggingface page the model weights are 44.5 Gb.
…
-
This issue tracks progress and understanding of the quantization problem. We will select a downstream task to fine-tune BERT and perform quantization-aware training. Then, we will take these quantized…
cjg91 updated
2 years ago
-
Hi,
Have you tried quantizing Mamba? Do you plan on releasing quantized versions?
Can you share your thoughts on quantizing Mamba, given the sensitivity of the model's recurrent dynamics?
Thanks
-
**Describe the bug**
What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程,最好有截图)
![图片](https://github.com/modelscope/swift/assets/77217949/6ef0a48d-25d6-45d7-965a-e5fa5ec7c98c)…
-
### Checklist
- [X] 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.…
vnkc1 updated
7 hours ago
-
I'm attempting to quantize the Cohere model using this repo as the base ([commit 6cf02f8d26edb63840f2aca34798befb48c95b38](https://github.com/casper-hansen/AutoAWQ/commit/6cf02f8d26edb63840f2aca34798b…
-
It seems that only weight quantization is supported in this repo, isn't it?
Do you have plan to release the implementation including activation quantization in the future?
-
I am trying to quantize mobilenet model in the same how you have implemented resnet (https://github.com/eladhoffer/convNet.pytorch). To accomplish this I added the following lines in models/mobilenet …