Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Flexible Pack DType #1158

Merged
merged 15 commits into from
Jan 26, 2025
Merged

Flexible Pack DType #1158

merged 15 commits into from
Jan 26, 2025

Conversation

Qubitium
Copy link
Collaborator

@Qubitium Qubitium commented Jan 24, 2025

Allow quantized weights to be packed in:

  • int32 (default, original gptq)
  • int16
  • int8

Some kernels/gpus may benefit to the different alignments for concurrent dequant

Completed Kernels:

  • Torch
  • Triton
  • Cuda
  • Exllama
  • Exllama v2
  • Marlin

@Qubitium Qubitium marked this pull request as ready for review January 26, 2025 02:46
@Qubitium Qubitium changed the title Flex Storage DType Flexible Pack DType Jan 26, 2025
@Qubitium Qubitium merged commit d6b9d9d into main Jan 26, 2025
2 of 4 checks passed
@Qubitium Qubitium deleted the flex-storage-dtype branch January 26, 2025 07:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants