MDK8888 / GPTFast

Accelerate your Hugging Face Transformers 6-8.5x. Native to Hugging Face and PyTorch.

MDK8888/GPTFast Issues

Set requirements to more flexible version
Updated a month ago
Help run GPTFast on Mistral-7B-v0.1 (or v.02) for CausalML
Updated 2 months ago1
Model Config settings for Llama-based architectures
Updated 2 months ago8
Help to run GPTFast on Mixtral-8x7B-Instruct-v0.1
Updated 2 months ago2
Update PyTorch to 2.2
Closed 2 months ago2
Doesn't work on kaggle notebooks - ValueError: Unable to compare versions for numpy>=1.17: need=1.17 found=None. This is unusual. Consider reinstalling numpy.
Updated 2 months ago
GPTFast 0.2.1: function argmax_variation() is not used
Updated 2 months ago
ERROR: No matching distribution found for triton==2.1.0
Closed 2 months ago2
Possible to use with a VL model like LLAVA?
Updated 2 months ago2
Help to understand
Updated 3 months ago6