Skip to content

Conversation

@thomasw21
Copy link
Contributor

No description provided.

@thomasw21 thomasw21 merged commit be8827f into main Oct 22, 2022
@thomasw21 thomasw21 deleted the add-license-1 branch October 22, 2022 08:44
sywangyi referenced this pull request in sywangyi/text-generation-inference Mar 12, 2024
@ismael-dm ismael-dm mentioned this pull request Oct 1, 2024
4 tasks
Narsil added a commit that referenced this pull request Oct 23, 2024
Narsil added a commit that referenced this pull request Oct 28, 2024
…2673)

* Choosing input/total tokens automatically based on available VRAM?

* Update doc.

* Remove generated files.

* Trying to fix non chunking targets.

* Attempt #2

* fix.

* QuantLinear is rocm compatible.

* Much simpler logic after the overhead.

* Updating logic + non flash.

* Revert doc text.

* Simple updates.

* Fix integration mt0 (transformers update).
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