Skip to content

Pull requests: HabanaAI/vllm-hpu-extension

New pull request New
9 Open 56 Closed
9 Open 56 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

allow lm_head quantization in calibration process
#65 opened Dec 23, 2024 by nirda7 Loading…
[WIP] Add option to do group sum on TPC instead of MME
#64 opened Dec 20, 2024 by mswiniarsk • Draft
Add exponential bucketing PoC
#61 opened Dec 17, 2024 by kzawora-intel • Draft
vLLM-Ext: Full enabling of ALiBi
#60 opened Dec 17, 2024 by tannervoas742 Loading…
Change repeat kv cache default and name convension
#56 opened Dec 11, 2024 by iboiko-habana Loading…
Introduce Pipelined PA in 1.19 release
#54 opened Dec 10, 2024 by mswiniarsk Loading…
Remove vllm.logger.init_logger dependency
#53 opened Dec 9, 2024 by kzawora-intel Loading…
Add AWQ class
#29 opened Nov 8, 2024 by maktukmak Loading…
1
Add GPTQ class
#28 opened Nov 8, 2024 by maktukmak Loading…
3
ProTip! no:milestone will show everything without a milestone.