-
**Describe the bug**
Performing https://github.com/vllm-project/llm-compressor/tree/main/examples/quantization_24_sparse_w4a16
```python
import os
import torch
from llmcompressor.transforme…
-
Goal: reduce inference time of the model using quantization
We made some CPU inference performance results public for 2021 in CMS, https://cds.cern.ch/record/2792320/files/DP2021_030.pdf slide 16, …
jpata updated
3 months ago
-
**Describe the bug**
When exporting the YOLOv8s (pruned50-quant, model.pt from sparsezoo) model via the ONNX exporter (sparseml.ultralytics.export_onnx), its performance noticeably decreases compar…
-
## 🐛 Bug
I am training my ConvNet model with OCT Data and analysing the privacy spent using Opacus by implementing the [Random Sparsification](https://github.com/JunyiZhu-AI/RandomSparsification)…
-
**Describe the bug**
RUN llm-compressor/examples/quantization_w8a8_fp8$ python llama3_example.py
save safetensors :KeyError: torch.float8_e4m3fn
**Expected behavior**
A clear and concise descri…
-
# Paper Information
- **Paper Title**: MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
- **Paper URL**: https://arxiv.org/pdf/2406.05927
- **Paper au…
-
### 🚀 The feature, motivation and pitch
I am trying to **train** ultra-sparse linear layers with as low as 0.1% of nonzero elements. Forward propagation is successful, however propagating the loss …
-
I tried to install Networkit version 7.1 with pip install networkit==7.1 it give me this error:
Collecting networkit==7.1
Using cached networkit-7.1.tar.gz (3.1 MB)
Preparing metadata (setu…
-
hi guys!
What is the plan and timescale of making this an installable python package? We are trying to use ASAP in a toolchain together with other tools, and finding it more difficult to work with …
-
Hi, Ziming!
While trying your very detailed tutorial, I’ve found a severe issue which may undermine the effectiveness of integrating KAN into other regular neural networks.
For instance, in tutori…