text-generation-inference
Improve support for GPUs with capability < 8
#2575
Merged

Improve support for GPUs with capability < 8 #2575

danieldk merged 4 commits into main from bugfix/pre-cc-8
danieldk
danieldk danieldk force pushed from 491c0269 to 5bd79b8a 1 year ago
danieldk Improve support for GPUs with capability < 8
bee5ee1f
danieldk nix: add flash-attn-v1 to the server environment
8c0f9312
danieldk danieldk force pushed from 5bd79b8a to 8c0f9312 1 year ago
danieldk danieldk marked this pull request as ready for review 1 year ago
Narsil
Narsil commented on 2024-09-27
Narsil
Narsil commented on 2024-09-27
Narsil
Narsil commented on 2024-09-27
Narsil
Narsil commented on 2024-09-27
danieldk Move disabling prefix caching into the block of exceptions
a29636ee
danieldk Capability as `usize`s
3eb68a37
danieldk danieldk requested a review from Narsil Narsil 1 year ago
Narsil
Narsil approved these changes on 2024-09-27
danieldk danieldk merged 5b6b74e2 into main 1 year ago
danieldk danieldk deleted the bugfix/pre-cc-8 branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone