Kusnezow94 comments

Repositories
Issues
Comments

Results 4 comments of


                                            Kusnezow94

[Feature]: GPT MODEL

Any Updates on this? Could be great to use 128K turbo model now..

CUDA based Pytorch Flash Attention is straight up non-functional / non-existent on Windows in ALL PyTorch versions above 2.1.2, opening this issue just to remove the weird vagueness around this.

Same issue, tried to use FLUX today, 12GB VRAM, 32GB RAM. But it straight up declines using flash att leading to 30 min generation time per image (20it). Completely unusable.

Fix header layout issue on high-DPI displays with scaling

@theguymadmax thanks for the kudos! Actually this "bigger" margin, is the standard master margin. It just gets smaller, because the master pushes the navigation down, without adjusting the margin for...

Other IDE support (JetBrains, VS2022, etc)

Bumb for PyCharm

Kusnezow94

[Feature]: GPT MODEL

CUDA based Pytorch Flash Attention is straight up non-functional / non-existent on Windows in *ALL* PyTorch versions above 2.1.2, opening this issue just to remove the weird vagueness around this.

Fix header layout issue on high-DPI displays with scaling

Other IDE support (JetBrains, VS2022, etc)

CUDA based Pytorch Flash Attention is straight up non-functional / non-existent on Windows in ALL PyTorch versions above 2.1.2, opening this issue just to remove the weird vagueness around this.