Fix NVFP4 FakeTensor compatibility with PyTorch 2.9.1#26
Open
wobba wants to merge 1 commit intodeepbeepmeep:mainfrom
Open
Fix NVFP4 FakeTensor compatibility with PyTorch 2.9.1#26wobba wants to merge 1 commit intodeepbeepmeep:mainfrom
wobba wants to merge 1 commit intodeepbeepmeep:mainfrom
Conversation
Add @torch.compiler.disable decorator to _lora_linear_forward method to prevent torch.compile from tracing through NVFP4 quantized weight operations, avoiding FakeTensor mixing errors in PyTorch 2.9.1+. This allows NVFP4 4-bit quantization to work correctly with RTX 50xx series GPUs and their optimized lightx2v kernels.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add @torch.compiler.disable decorator to _lora_linear_forward method to prevent torch.compile from tracing through NVFP4 quantized weight operations, avoiding FakeTensor mixing errors in PyTorch 2.9.1+.
This allows NVFP4 4-bit quantization to work correctly with RTX 50xx series GPUs and their optimized lightx2v kernels.