Skip to content

Conversation

@Nexesenex
Copy link
Owner

No description provided.

nopperl and others added 3 commits April 19, 2024 11:35
* implement olmo architecture

* remove unused variable

* remove unused moe branch

* remove check for weight

* remove superfluous moe, bias and rope tensors

* clarified comment

* fix clamp_kqv setting

* remove obsolete parameter name filter
@Nexesenex Nexesenex merged commit c46ce14 into Nexesenex:downstream Apr 19, 2024
Nexesenex pushed a commit that referenced this pull request Dec 22, 2024
* iq1_bn: improve CUDA TG

On RTX-3080 TG-128(Bitnet-1.58b-3B) goes from 318 t/s to 340 t/s.
I see I have on the front page 301 t/s, so pretty nice improvement
since then.

* iq2_bn(CUDA): quants are not 4-byte aligned

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex pushed a commit that referenced this pull request Feb 25, 2025
* iq1_bn: improve CUDA TG

On RTX-3080 TG-128(Bitnet-1.58b-3B) goes from 318 t/s to 340 t/s.
I see I have on the front page 301 t/s, so pretty nice improvement
since then.

* iq2_bn(CUDA): quants are not 4-byte aligned

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
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.

4 participants