text-generation-inference
Add support for exl2-quantized models
#1965
Merged

Add support for exl2-quantized models #1965

danieldk merged 2 commits into main from feature/exl2
danieldk
danieldk danieldk force pushed from 17511ed5 to 051690c0 2 years ago
danieldk danieldk changed the title Feature/exl2 Add support for exl2-quantized models 2 years ago
HuggingFaceDocBuilderDev
danieldk danieldk force pushed from 051690c0 to 310ae0fa 2 years ago
danieldk danieldk force pushed from 310ae0fa to ac30a295 2 years ago
danieldk danieldk force pushed from ac30a295 to 507bfa04 2 years ago
danieldk danieldk force pushed from 507bfa04 to f3e8eaca 2 years ago
danieldk danieldk force pushed from f3e8eaca to 8e030246 2 years ago
danieldk danieldk marked this pull request as ready for review 2 years ago
danieldk danieldk force pushed from 8e030246 to e3856cdb 2 years ago
Narsil
Narsil commented on 2024-05-29
danieldk danieldk force pushed from e3856cdb to 69daaa5b 2 years ago
Narsil
Narsil commented on 2024-05-29
danieldk danieldk force pushed from 69daaa5b to d14c046c 2 years ago
danieldk danieldk force pushed from d14c046c to 4057345b 2 years ago
danieldk Add support for exl2 quantization
3fa24fb2
danieldk danieldk force pushed from 4057345b to 3fa24fb2 2 years ago
danieldk Gemma GPTQ checks: skip logprob checks
03699839
danieldk danieldk requested a review from Narsil Narsil 2 years ago
Narsil
Narsil approved these changes on 2024-05-30
danieldk danieldk merged 967ced2f into main 2 years ago
danieldk danieldk deleted the feature/exl2 branch 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone