Skip to content

Pull requests: bytedance/byteir

New pull request New
20 Open 458 Closed
20 Open 458 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[torch-frontend] use new register method to register byteir.flash_att…
#473 opened Oct 25, 2024 by qingyunqu Loading…
fix slice opt returns copy
#418 opened Aug 7, 2024 by YellowHCH Loading…
[compiler] Horizontal fusion
#395 opened Jul 8, 2024 by YellowHCH Loading…
3
[compiler] add forall-tiling pass enhancement New feature or request
#370 opened Jun 24, 2024 by XG-zheng Loading…
[compiler] fold mhlo.reduce with splat input
#367 opened Jun 24, 2024 by jianwenyyy Loading…
[WIP] Add multi stream execute plan
#340 opened Jun 16, 2024 by Xinyu302 Loading…
1
[compiler] try to reorder byre.copy to overlap IO and compute
#332 opened Jun 13, 2024 by YellowHCH • Draft
[dynamo] reduce host side overhead
#328 opened Jun 12, 2024 by YellowHCH Loading…
1
[GEMM codegen] Add e2e pipeline
#316 opened Jun 7, 2024 by Xinyu302 Loading…
1
[runtime] add BatchTranspose cuda kernel enhancement New feature or request
#309 opened Jun 5, 2024 by XG-zheng Loading…
[torch-frontend] fx export FakeTensor weight as SplatElementsAttr.
#299 opened May 30, 2024 by Vremold Loading…
Training
#296 opened May 30, 2024 by YellowHCH • Draft
[fix] Update prepare.sh to prevent deletion of 'external_libs/libs' before rebuilding runtime
#270 opened May 22, 2024 by Xinyu302 Loading…
1
[WIP][E2E]Fix e2e errors
#258 opened May 18, 2024 by Xinyu302 Loading…
1
[torch-frontend] add stablehlo IRs for Mixtral model. enhancement New feature or request
#254 opened May 16, 2024 by Vremold Loading…
1
[compiler] support shape reification for callOp enhancement New feature or request
#182 opened Apr 7, 2024 by XG-zheng Loading…
[Runtime]Add runtime dynamic shared mem support enhancement New feature or request
#179 opened Apr 2, 2024 by Xinyu302 Loading…
1
WIP: [compiler] implement reduction with gpu shuffle enhancement New feature or request
#171 opened Mar 28, 2024 by Mi-Jiazhi Loading…
[draft][runtime] modified OpKernel to support dynamic shape enhancement New feature or request
#162 opened Mar 25, 2024 by XG-zheng • Draft
[Doc] Update gpu.md documentation Improvements or additions to documentation
#8 opened Feb 20, 2023 by lchang20 Loading…
3
ProTip! no:milestone will show everything without a milestone.