Skip to content

Pull requests: HabanaAI/vllm-hpu-extension

New pull request New
7 Open 22 Closed
7 Open 22 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add AWQ class
#29 opened Nov 8, 2024 by maktukmak Loading…
Add GPTQ class
#28 opened Nov 8, 2024 by maktukmak Loading…
do not use softmax fast mode in FusedSDPA
#26 opened Nov 5, 2024 by ccrhx4 Loading…
1
Add VLLM_PA_SOFTMAX_IMPL='const' to bring back magic value
#24 opened Nov 1, 2024 by xuechendi Loading…
5
Remove uncessary repeat cache when FusedSdpa is used.
#21 opened Oct 29, 2024 by libinta Loading…
1
Resolved alibi bias issue by reverting to PA v1.
#19 opened Oct 28, 2024 by tannervoas742 Loading…
1
Resolved alibi bias issue due to porting flat PA pr
#18 opened Oct 28, 2024 by tannervoas742 Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.