Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / mit-han-lab/llm-awq issues and pull requests

#12 - Question about apply scales for fc2

Issue - State: closed - Opened by Taka152 over 1 year ago - 3 comments

#11 - Help me understand, this is weight only quant?

Issue - State: closed - Opened by JianbangZ over 1 year ago - 3 comments

#10 - A question about the metrics in the paper

Issue - State: closed - Opened by loklok-infi over 1 year ago - 6 comments

#9 - Question: Mismatched CUDA version (12.0)

Issue - State: open - Opened by rubydoudou over 1 year ago - 1 comment

#8 - [DEBUG] Fix W4A16 CUDA kernel launching bug.

Pull Request - State: closed - Opened by ys-2020 over 1 year ago

#7 - 4bit kernel error when large input size

Issue - State: open - Opened by Tracin over 1 year ago - 4 comments

#6 - how to use awq in our own model?

Issue - State: open - Opened by EveningLin over 1 year ago - 2 comments

#5 - Support for MPT models

Issue - State: closed - Opened by casper-hansen over 1 year ago - 2 comments

#4 - Which "activations" are assumed in this work?

Issue - State: closed - Opened by Andrey36652 over 1 year ago - 2 comments

#3 - 3bit backward implementation

Issue - State: closed - Opened by qwopqwop200 over 1 year ago - 1 comment

#2 - How can I make it support Bloom?

Issue - State: closed - Opened by Tracin over 1 year ago - 15 comments

#1 - Does this work support compression and acceleration for mt0-xl or gpt model?

Issue - State: open - Opened by songkq over 1 year ago - 2 comments