Skip to content

Pull requests: intel/xFasterTransformer

New pull request New
8 Open 383 Closed
8 Open 383 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 bf16_int8 support for invokeLayerLLaMA API
#470 opened Jul 22, 2024 by miaojinc Loading…
Add env param KV_CACHE_LOCATION to control kv cache memory numanode location
#462 opened Jun 28, 2024 by a3213105 Loading…
6
[Model] Group support for int8/int4 models
#461 opened Jun 26, 2024 by xiangzez • Draft
[Layers] Increased the threshold for enabling flashAttn performance performance related.
#428 opened Jun 3, 2024 by abenmao Loading…
[Kernel] Add dynamic onednn matmul. performance performance related.
#425 opened May 28, 2024 by changqi1 Loading…
[Model] Achieve whole pipeline parallel. enhancement New feature or request gpu Related to GPU
#355 opened Apr 28, 2024 by changqi1 • Draft
1
[Eval] Add eval test with opencompass. benchmark performance or accuracy benchmark enhancement New feature or request
#325 opened Apr 17, 2024 by marvin-Yu • Draft
1
Update AWQ GPTQ quantization guide documentation Improvements or additions to documentation
#306 opened Apr 10, 2024 by miaojinc Loading…
@pujiang2018
2
ProTip! What’s not been updated in a month: updated:<2024-06-22.